Duplicate from Qiskit/ai-transpiler_linear-functions

Co-authored-by: Victor <victor79@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,108 @@
+---
+license: apache-2.0
+---
+
+![hf-banner-ai-transpiler_linear-functions](https://cdn-uploads.huggingface.co/production/uploads/64b7001445f3511db2f6aa5b/VJV29bWXra2KnMCWcZ1D4.png)
+
+# Linear Function Quantum Synthesis Circuit Models
+
+## Introduction
+This repository hosts models for linear function synthesis in quantum circuits trained with RL techniques. The models are specialized for different topologies up to 10 qubits. 
+
+A linear function over n qubits is an n×n binary transformation on X/Z operators (the reversible linear part of a Clifford). Implementing it means finding CX/SWAP-based circuits whose action matches that binary map. [More information about Linear Funtion circuits](https://quantum.cloud.ibm.com/docs/en/api/qiskit/qiskit.circuit.library.LinearFunction)
+
+For each model, there is the environment configs (`.json`) and the trained policy weights (`.safetensors`).
+
+
+## Scope
+- Linear-function synthesis models.
+- Each model is tied to a specific qubit count and topology; use the matching pair for your target device/layout. To discover the specific topology for each model see the `gateset` property in the model's config.
+
+## Contents
+- `linear_function_*.json`: model configs for a given qubit count/topology.
+- Matching `.safetensors` files: trained policies for each JSON (same filename stem).
+
+
+## Training
+
+Training data is entirely synthetic and generated internally at IBM Quantum using custom reinforcement learning environments built on [Qiskit-Gym](https://github.com/AI4quantum/qiskit-gym).
+
+**Data Collection:** Target operators are generated by sampling random linear-reversible circuits with CNOT gates consistent with the target coupling map. The number of gates scales with the difficulty, which increase when the model learns to solve circuits at that difficulty. No external datasets or third-party circuit repositories are used.
+
+**PII:** No personal or sensitive data is present or used in any phase of training, as all data is synthetic and generated algorithmically.
+
+**Infrastructure:** We train the models using IBM's Cognitive Computing Cluster (CCC) using NVIDIA A100 40GB GPUs. The cluster provides a scalable and efficient infrastructure for training.
+
+
+## Usage example
+
+Here we provide a code snippet to synthesis a random 10qL linear function. In addition to the model we use the `qiskit-gym` ([repo](https://github.com/AI4quantum/qiskit-gym)) and `twisteRL` ([repo](https://github.com/AI4quantum/twisteRL)) libraries, as well as `qiskit`. You can install all needed libraries running `pip install qiskit-gym` in your python virutal environment.
+
+```python
+from qiskit_gym.rl import RLSynthesis
+
+from twisterl.utils import pull_hub_algorithm
+
+from qiskit.circuit.library import LinearFunction
+from qiskit.synthesis.linear.linear_matrix_utils import random_invertible_binary_matrix
+
+local_path = pull_hub_algorithm(
+    repo_id="Qiskit/ai-transpiler_linear-functions",
+    model_path="./models",
+    revision="main",
+    validate=True
+)
+
+if not local_path:
+    raise ValueError("Failed to download model from hub")
+
+num_qubits = 10
+matrix = random_invertible_binary_matrix(num_qubits, seed=42)
+input_lf = LinearFunction(matrix)
+rls = RLSynthesis.from_config_json(f"{local_path}/linear_function_10qL.json", f"{local_path}/linear_function_10qL.safetensors")
+qc_lf_output = rls.synth(input_lf, num_searches=10, num_mcts_searches=0, deterministic=False)
+print(qc_lf_output)
+```
+
+<!-- MODEL_INDEX_START -->
+## Models
+
+Below is the list of available models with qubit counts and topologies:
+
+| Model | Qubits | Topology |
+| --- | --- | --- |
+| [`linear_function_2qL`](model_data/linear_function_2qL.md) | 2 | L |
+| [`linear_function_3qL`](model_data/linear_function_3qL.md) | 3 | L |
+| [`linear_function_4qL`](model_data/linear_function_4qL.md) | 4 | L |
+| [`linear_function_4qY`](model_data/linear_function_4qY.md) | 4 | Y |
+| [`linear_function_5qL`](model_data/linear_function_5qL.md) | 5 | L |
+| [`linear_function_5qT`](model_data/linear_function_5qT.md) | 5 | T |
+| [`linear_function_6qL`](model_data/linear_function_6qL.md) | 6 | L |
+| [`linear_function_6qT`](model_data/linear_function_6qT.md) | 6 | T |
+| [`linear_function_6qY`](model_data/linear_function_6qY.md) | 6 | Y |
+| [`linear_function_7qF`](model_data/linear_function_7qF.md) | 7 | F |
+| [`linear_function_7qH`](model_data/linear_function_7qH.md) | 7 | H |
+| [`linear_function_7qL`](model_data/linear_function_7qL.md) | 7 | L |
+| [`linear_function_7qT`](model_data/linear_function_7qT.md) | 7 | T |
+| [`linear_function_7qY`](model_data/linear_function_7qY.md) | 7 | Y |
+| [`linear_function_8qF`](model_data/linear_function_8qF.md) | 8 | F |
+| [`linear_function_8qJ`](model_data/linear_function_8qJ.md) | 8 | J |
+| [`linear_function_8qL`](model_data/linear_function_8qL.md) | 8 | L |
+| [`linear_function_8qT1`](model_data/linear_function_8qT1.md) | 8 | T1 |
+| [`linear_function_8qT2`](model_data/linear_function_8qT2.md) | 8 | T2 |
+| [`linear_function_8qY`](model_data/linear_function_8qY.md) | 8 | Y |
+| [`linear_function_9qF1`](model_data/linear_function_9qF1.md) | 9 | F1 |
+| [`linear_function_9qF2`](model_data/linear_function_9qF2.md) | 9 | F2 |
+| [`linear_function_9qH1`](model_data/linear_function_9qH1.md) | 9 | H1 |
+| [`linear_function_9qH2`](model_data/linear_function_9qH2.md) | 9 | H2 |
+| [`linear_function_9qH3`](model_data/linear_function_9qH3.md) | 9 | H3 |
+| [`linear_function_9qJ`](model_data/linear_function_9qJ.md) | 9 | J |
+| [`linear_function_9qL`](model_data/linear_function_9qL.md) | 9 | L |
+| [`linear_function_9qT1`](model_data/linear_function_9qT1.md) | 9 | T1 |
+| [`linear_function_9qT2`](model_data/linear_function_9qT2.md) | 9 | T2 |
+| [`linear_function_9qY`](model_data/linear_function_9qY.md) | 9 | Y |
+| [`linear_function_10qL`](model_data/linear_function_10qL.md) | 10 | L |
+<!-- MODEL_INDEX_END -->
+
+## Acknowledgements
+The authors acknowledge the IBM Research CCC Service for providing resources that have contributed to the production or processing of the data contained within this data collection.

config.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "reinforcement_learning",
+  "task": "quantum_circuit_synthesis",
+  "problem_type": "linear_function_synthesis",
+  "framework": "qiskit-gym",
+  "license": "apache-2.0",
+  "tags": ["quantum-computing", "reinforcement-learning", "circuit-synthesis", "qiskit", "quantum-transpilation", "linear-function-synthesis"],
+  "paper": {
+    "title": "Practical and efficient quantum circuit synthesis and transpiling with reinforcement learning",
+    "authors": ["Kremer, D.", "Villar, V.", "Paik, H.", "Duran, I.", "Faro, I.", "Cruz-Benito, J."],
+    "arxiv": "2405.13196",
+    "year": 2024
+  }
+}

linear_function_10qL.json

@@ -0,0 +1,198 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 10,
+    "difficulty": 1024,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          8
+        ]
+      ],
+      [
+        "CX",
+        [
+          8,
+          7
+        ]
+      ],
+            [
+        "CX",
+        [
+          8,
+          9
+        ]
+      ],
+      [
+        "CX",
+        [
+          9,
+          8
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.1,
+      "n_layers_cnots": 0.05,
+      "n_layers": 0.05,
+      "n_gates": 0.1
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_10qL.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e559506bc70cb7f6523504243107bacd3eab62030920549985e0b4490a89aa4e
+size 752324

linear_function_2qL.json

@@ -0,0 +1,86 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 2,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 128,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 256,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_2qL.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a887a968b9a3c8df8e4c3608901abea320ae5bd0ecd340bef324b16e68f72ba0
+size 539260

linear_function_3qL.json

@@ -0,0 +1,100 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 3,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 128,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 256,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_3qL.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2889afd849a7da4e0b01f3e5b1bb7cc206784202d2dbfa07020e190ace7bfa96
+size 551556

linear_function_4qL.json

@@ -0,0 +1,114 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 4,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          0,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 128,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 256,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_4qL.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:171b540a6c0060dc74395491afde4631516e5f2169dd00fae54736037e500f4f
+size 567948

linear_function_4qY.json

@@ -0,0 +1,114 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 4,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 128,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 256,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_4qY.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cb13d7c38e282fe129a1d837a374e0cf01e676fdf6a6b013aa2d11ad5df305
+size 567948

linear_function_5qL.json

@@ -0,0 +1,128 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 5,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 128,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 256,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_5qL.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ec15fac122616f8d43d707af4b7adfe800bb58281f56f628e3cc6bc3c58972
+size 588436

linear_function_5qT.json

@@ -0,0 +1,128 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 5,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 128,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 256,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_5qT.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ac5ca65b91c0442ca1e30e2f1270bbf2490b74fef32317bc78eea7d002a583
+size 588436

linear_function_6qL.json

@@ -0,0 +1,142 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 6,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_6qL.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b841f05b6489e7a44d45bfa643df096eb516e3bac001325a1ffc093033f108a5
+size 613028

linear_function_6qT.json

@@ -0,0 +1,142 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 6,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_6qT.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085fcb02ab416a1009b066229df858be88262c59b7dab1effb21b52c01e98fa2
+size 613028

linear_function_6qY.json

@@ -0,0 +1,142 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 6,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_6qY.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45576b41263c6931e4238ed3ea03c1e9cd5f4e16275b008f48ed9807a5bfe903
+size 613028

linear_function_7qF.json

@@ -0,0 +1,156 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 7,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_7qF.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79bbecbab1c66ef1c6456140a32589362857aeb56cff3df9999e5bb7a71e95f
+size 641708

linear_function_7qH.json

@@ -0,0 +1,156 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 7,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          4
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_7qH.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef82a76f243309557b9678060d26c8629204e7706873b840d3e61068085c8a9
+size 641708

linear_function_7qL.json

@@ -0,0 +1,156 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 7,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_7qL.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f287665ea48dc31c6e6205a9adf13f1304140b4b578a09684787ec246314c62e
+size 641708

linear_function_7qT.json

@@ -0,0 +1,156 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 7,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_7qT.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f663d35da85f873afd0412b401a99068d05f07af547e883c89dde39ac8078dc
+size 641708

linear_function_7qY.json

@@ -0,0 +1,156 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 7,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_7qY.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71de5af50f3e947469e3ec94b3842c238d74e1ba504d17202d7c550b99e849dc
+size 641708

linear_function_8qF.json

@@ -0,0 +1,170 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 8,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_8qF.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c8eedcd0511bb869738aa874790a4feb9fad0412d8bcbceddf5b0efd71be24
+size 674484

linear_function_8qJ.json

@@ -0,0 +1,170 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 8,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_8qJ.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530489587bdf5830da0894f11fa41319d12c9068654e6985a08af6474bc6976b
+size 674484

linear_function_8qL.json

@@ -0,0 +1,170 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 8,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 256,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 512,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_8qL.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d1174450d4206bacd61eaf81338913040a042fcab050f3acacc1ee4de69074
+size 674484

linear_function_8qT1.json

@@ -0,0 +1,170 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 8,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_8qT1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a5a030b43018ea6abdb90ef45a54a03345e07397924be8bab9edb1e0ce0c83
+size 674484

linear_function_8qT2.json

@@ -0,0 +1,170 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 8,
+    "difficulty": 1024,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.05,
+      "n_layers_cnots": 0.05,
+      "n_layers": 0.05,
+      "n_gates": 0.05
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_8qT2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1406279b3dd5a29e6475b0c23860e2a97948245c27db26854f6958b3d65cb88b
+size 674484

linear_function_8qY.json

@@ -0,0 +1,170 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 8,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          4
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_8qY.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39f56e015898a58a9a0a5c4d5c36fce83f5872a46e1b09ee470f32548fef50f
+size 674484

linear_function_9qF1.json

@@ -0,0 +1,184 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 9,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          8
+        ]
+      ],
+      [
+        "CX",
+        [
+          8,
+          7
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_9qF1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f23669102b162c2a2d35eaa580744b760198de8bd375d7ca6c3e2a1b6cd986c9
+size 711356

linear_function_9qF2.json

@@ -0,0 +1,184 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 9,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          8
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          8,
+          5
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}

linear_function_9qF2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484e6e360286933e0846774cc9e0fc40d224a7f51c30d365edf066bce2ce6377
+size 711356

linear_function_9qH1.json

@@ -0,0 +1,184 @@
+{
+  "env_cls": "qiskit_gym.envs.synthesis.LinearFunctionEnv",
+  "env": {
+    "num_qubits": 9,
+    "difficulty": 1,
+    "gateset": [
+      [
+        "CX",
+        [
+          0,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          1,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          0
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          1
+        ]
+      ],
+      [
+        "CX",
+        [
+          2,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          2
+        ]
+      ],
+      [
+        "CX",
+        [
+          3,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          4,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          3
+        ]
+      ],
+      [
+        "CX",
+        [
+          5,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          5
+        ]
+      ],
+      [
+        "CX",
+        [
+          6,
+          7
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          4
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          6
+        ]
+      ],
+      [
+        "CX",
+        [
+          7,
+          8
+        ]
+      ],
+      [
+        "CX",
+        [
+          8,
+          7
+        ]
+      ]
+    ],
+    "depth_slope": 2,
+    "max_depth": 512,
+    "metrics_weights": {
+      "n_cnots": 0.01,
+      "n_layers_cnots": 0.01,
+      "n_layers": 0.01,
+      "n_gates": 0.01
+    }
+  },
+  "policy_cls": "twisterl.nn.BasicPolicy",
+  "policy": {
+    "embedding_size": 512,
+    "common_layers": [
+      256
+    ],
+    "policy_layers": [],
+    "value_layers": []
+  },
+  "algorithm_cls": "twisterl.rl.PPO",
+  "algorithm": {
+    "collecting": {
+      "num_cores": 32,
+      "num_episodes": 1024,
+      "lambda": 0.995,
+      "gamma": 0.995
+    },
+    "training": {
+      "num_epochs": 10,
+      "vf_coef": 0.8,
+      "ent_coef": 0.01,
+      "clip_ratio": 0.1,
+      "normalize_advantage": false
+    },
+    "learning": {
+      "diff_threshold": 0.85,
+      "diff_max": 1024,
+      "diff_metric": "ppo_deterministic"
+    },
+    "optimizer": {
+      "lr": 0.0003
+    },
+    "evals": {
+      "ppo_deterministic": {
+        "num_episodes": 100,
+        "deterministic": true,
+        "num_searches": 1,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      },
+      "ppo_10": {
+        "num_episodes": 100,
+        "deterministic": false,
+        "num_searches": 10,
+        "num_mcts_searches": 0,
+        "num_cores": 32,
+        "C": 1.41
+      }
+    },
+    "logging": {
+      "log_freq": 1,
+      "checkpoint_freq": 10
+    }
+  }
+}