Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-Huggy
Instructions to use Nishant91/ppo-Huggy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use Nishant91/ppo-Huggy with ml-agents:
mlagents-load-from-hf --repo-id="Nishant91/ppo-Huggy" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from Nishant91/ppo-Huggy: direct link, hf CLI and curl.
- Browser
- Download file 17.9 kB
-
https://huggingface.co/Nishant91/ppo-Huggy/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://Nishant91/ppo-Huggy/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/Nishant91/ppo-Huggy/resolve/main/run_logs/timers.json
17.9 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "Huggy.Policy.Entropy.mean": { | |
| "value": 1.4041695594787598, | |
| "min": 1.4041695594787598, | |
| "max": 1.4272457361221313, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.Entropy.sum": { | |
| "value": 69825.140625, | |
| "min": 67993.65625, | |
| "max": 77364.859375, | |
| "count": 40 | |
| }, | |
| "Huggy.Environment.EpisodeLength.mean": { | |
| "value": 86.69001751313485, | |
| "min": 73.87724550898204, | |
| "max": 397.6746031746032, | |
| "count": 40 | |
| }, | |
| "Huggy.Environment.EpisodeLength.sum": { | |
| "value": 49500.0, | |
| "min": 48769.0, | |
| "max": 50149.0, | |
| "count": 40 | |
| }, | |
| "Huggy.Step.mean": { | |
| "value": 1999340.0, | |
| "min": 49827.0, | |
| "max": 1999340.0, | |
| "count": 40 | |
| }, | |
| "Huggy.Step.sum": { | |
| "value": 1999340.0, | |
| "min": 49827.0, | |
| "max": 1999340.0, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 2.42406964302063, | |
| "min": 0.1721307635307312, | |
| "max": 2.5011255741119385, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 1384.143798828125, | |
| "min": 21.516345977783203, | |
| "max": 1621.010009765625, | |
| "count": 40 | |
| }, | |
| "Huggy.Environment.CumulativeReward.mean": { | |
| "value": 3.720692450236105, | |
| "min": 1.7613751003146172, | |
| "max": 4.008709502100144, | |
| "count": 40 | |
| }, | |
| "Huggy.Environment.CumulativeReward.sum": { | |
| "value": 2124.515389084816, | |
| "min": 220.17188753932714, | |
| "max": 2546.8656062483788, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.ExtrinsicReward.mean": { | |
| "value": 3.720692450236105, | |
| "min": 1.7613751003146172, | |
| "max": 4.008709502100144, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.ExtrinsicReward.sum": { | |
| "value": 2124.515389084816, | |
| "min": 220.17188753932714, | |
| "max": 2546.8656062483788, | |
| "count": 40 | |
| }, | |
| "Huggy.Losses.PolicyLoss.mean": { | |
| "value": 0.01590058833858671, | |
| "min": 0.013657696535422776, | |
| "max": 0.019484661368187516, | |
| "count": 40 | |
| }, | |
| "Huggy.Losses.PolicyLoss.sum": { | |
| "value": 0.04770176501576013, | |
| "min": 0.027315393070845552, | |
| "max": 0.056696337403263894, | |
| "count": 40 | |
| }, | |
| "Huggy.Losses.ValueLoss.mean": { | |
| "value": 0.052756535510222115, | |
| "min": 0.020140024740248917, | |
| "max": 0.06424077960352104, | |
| "count": 40 | |
| }, | |
| "Huggy.Losses.ValueLoss.sum": { | |
| "value": 0.15826960653066635, | |
| "min": 0.040280049480497834, | |
| "max": 0.1927223388105631, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.LearningRate.mean": { | |
| "value": 3.7252987582666613e-06, | |
| "min": 3.7252987582666613e-06, | |
| "max": 0.0002953460265513249, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.LearningRate.sum": { | |
| "value": 1.1175896274799983e-05, | |
| "min": 1.1175896274799983e-05, | |
| "max": 0.0008438767687077501, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.Epsilon.mean": { | |
| "value": 0.10124173333333335, | |
| "min": 0.10124173333333335, | |
| "max": 0.19844867499999996, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.Epsilon.sum": { | |
| "value": 0.30372520000000003, | |
| "min": 0.20760550000000005, | |
| "max": 0.58129225, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.Beta.mean": { | |
| "value": 7.196249333333325e-05, | |
| "min": 7.196249333333325e-05, | |
| "max": 0.004922588882499999, | |
| "count": 40 | |
| }, | |
| "Huggy.Policy.Beta.sum": { | |
| "value": 0.00021588747999999976, | |
| "min": 0.00021588747999999976, | |
| "max": 0.014066483275, | |
| "count": 40 | |
| }, | |
| "Huggy.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 40 | |
| }, | |
| "Huggy.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 40 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1672422291", | |
| "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", | |
| "mlagents_version": "0.29.0.dev0", | |
| "mlagents_envs_version": "0.29.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.8.1+cu102", | |
| "numpy_version": "1.21.6", | |
| "end_time_seconds": "1672424620" | |
| }, | |
| "total": 2329.765257987, | |
| "count": 1, | |
| "self": 0.3884646659998907, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.1055215459999772, | |
| "count": 1, | |
| "self": 0.1055215459999772 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2329.271271775, | |
| "count": 1, | |
| "self": 4.092018536007799, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 7.95282526799997, | |
| "count": 1, | |
| "self": 7.95282526799997 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2317.109776118992, | |
| "count": 232904, | |
| "self": 4.363096719120676, | |
| "children": { | |
| "env_step": { | |
| "total": 1836.2209085988898, | |
| "count": 232904, | |
| "self": 1547.3620905619268, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 286.1815967850065, | |
| "count": 232904, | |
| "self": 14.781437314065442, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 271.40015947094105, | |
| "count": 222918, | |
| "self": 67.52901022093101, | |
| "children": { | |
| "TorchPolicy.sample_actions": { | |
| "total": 203.87114925001003, | |
| "count": 222918, | |
| "self": 203.87114925001003 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.677221251956553, | |
| "count": 232904, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2321.0013428478965, | |
| "count": 232904, | |
| "is_parallel": true, | |
| "self": 1046.897682327889, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0019594620000589202, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00037142099995435274, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0015880410001045675, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0015880410001045675 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.030563237000023946, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00031387200010613014, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00019566799994663597, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00019566799994663597 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.029363234000015837, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.029363234000015837 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0006904629999553435, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0002465899999606336, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.00044387299999470997, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.00044387299999470997 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1274.1036605200075, | |
| "count": 232903, | |
| "is_parallel": true, | |
| "self": 36.238178374210975, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 82.04877167887344, | |
| "count": 232903, | |
| "is_parallel": true, | |
| "self": 82.04877167887344 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1056.3984492770142, | |
| "count": 232903, | |
| "is_parallel": true, | |
| "self": 1056.3984492770142 | |
| }, | |
| "steps_from_proto": { | |
| "total": 99.41826118990889, | |
| "count": 232903, | |
| "is_parallel": true, | |
| "self": 43.00753148095134, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 56.41072970895755, | |
| "count": 465806, | |
| "is_parallel": true, | |
| "self": 56.41072970895755 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 476.5257708009816, | |
| "count": 232904, | |
| "self": 6.283858994870798, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 158.00519450211084, | |
| "count": 232904, | |
| "self": 156.84223151911044, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 1.1629629830003978, | |
| "count": 10, | |
| "self": 1.1629629830003978 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 312.23671730399997, | |
| "count": 97, | |
| "self": 259.74040501400805, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 52.49631228999192, | |
| "count": 2910, | |
| "self": 52.49631228999192 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.1309998626529705e-06, | |
| "count": 1, | |
| "self": 1.1309998626529705e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.11665072100004181, | |
| "count": 1, | |
| "self": 0.0029256469997562817, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.11372507400028553, | |
| "count": 1, | |
| "self": 0.11372507400028553 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |