poca-SoccerTwos / run_logs /timers.json
MindNetML's picture
First Push
1b7d43c
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.7540055513381958,
"min": 1.7540055513381958,
"max": 2.859694480895996,
"count": 287
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 34350.4453125,
"min": 25404.435546875,
"max": 68697.859375,
"count": 287
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 59.951219512195124,
"min": 45.43119266055046,
"max": 134.75675675675674,
"count": 287
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19664.0,
"min": 6264.0,
"max": 22528.0,
"count": 287
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1547.7343081913593,
"min": 1280.498417173598,
"max": 1573.583713813668,
"count": 287
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 253828.42654338293,
"min": 57443.42553063212,
"max": 334909.4936858504,
"count": 287
},
"SoccerTwos.Step.mean": {
"value": 4999964.0,
"min": 2139961.0,
"max": 4999964.0,
"count": 287
},
"SoccerTwos.Step.sum": {
"value": 4999964.0,
"min": 2139961.0,
"max": 4999964.0,
"count": 287
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.05619893968105316,
"min": -0.09217312932014465,
"max": 0.2106694132089615,
"count": 287
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 9.216626167297363,
"min": -14.655527114868164,
"max": 26.543701171875,
"count": 287
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.05358322709798813,
"min": -0.09259972721338272,
"max": 0.20666013658046722,
"count": 287
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 8.787649154663086,
"min": -14.723356246948242,
"max": 27.162918090820312,
"count": 287
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 287
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 287
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.029275610316090467,
"min": -0.3304608697476594,
"max": 0.3157929830383836,
"count": 287
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 4.801200091838837,
"min": -40.803199887275696,
"max": 54.64700049161911,
"count": 287
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.029275610316090467,
"min": -0.3304608697476594,
"max": 0.3157929830383836,
"count": 287
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 4.801200091838837,
"min": -40.803199887275696,
"max": 54.64700049161911,
"count": 287
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 287
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 287
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.017620729313542447,
"min": 0.011048298924288246,
"max": 0.02409756457200274,
"count": 138
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.017620729313542447,
"min": 0.011048298924288246,
"max": 0.02409756457200274,
"count": 138
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.1136249082783858,
"min": 0.04968581423163414,
"max": 0.1136249082783858,
"count": 138
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.1136249082783858,
"min": 0.04968581423163414,
"max": 0.1136249082783858,
"count": 138
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.11541301185886065,
"min": 0.050460034608840944,
"max": 0.11541301185886065,
"count": 138
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.11541301185886065,
"min": 0.050460034608840944,
"max": 0.11541301185886065,
"count": 138
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 138
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 138
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 138
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 138
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 138
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 138
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688065979",
"python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]",
"command_line_arguments": "/root/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688072947"
},
"total": 6967.477507870994,
"count": 1,
"self": 0.4749574410961941,
"children": {
"run_training.setup": {
"total": 0.018960394896566868,
"count": 1,
"self": 0.018960394896566868
},
"TrainerController.start_learning": {
"total": 6966.983590035001,
"count": 1,
"self": 7.383688202360645,
"children": {
"TrainerController._reset_env": {
"total": 8.599591638776474,
"count": 16,
"self": 8.599591638776474
},
"TrainerController.advance": {
"total": 6950.742673392873,
"count": 197041,
"self": 7.936746210791171,
"children": {
"env_step": {
"total": 5466.461122430745,
"count": 197041,
"self": 4434.788273636135,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1027.343017456471,
"count": 197041,
"self": 40.67520230030641,
"children": {
"TorchPolicy.evaluate": {
"total": 986.6678151561646,
"count": 359170,
"self": 986.6678151561646
}
}
},
"workers": {
"total": 4.3298313381383196,
"count": 197041,
"self": 0.0,
"children": {
"worker_root": {
"total": 6951.302592928172,
"count": 197041,
"is_parallel": true,
"self": 3226.155462664552,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031961901113390923,
"count": 2,
"is_parallel": true,
"self": 0.000803773058578372,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023924170527607203,
"count": 8,
"is_parallel": true,
"self": 0.0023924170527607203
}
}
},
"UnityEnvironment.step": {
"total": 0.040917290025390685,
"count": 1,
"is_parallel": true,
"self": 0.001090687932446599,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007754210382699966,
"count": 1,
"is_parallel": true,
"self": 0.0007754210382699966
},
"communicator.exchange": {
"total": 0.03585985500831157,
"count": 1,
"is_parallel": true,
"self": 0.03585985500831157
},
"steps_from_proto": {
"total": 0.0031913260463625193,
"count": 2,
"is_parallel": true,
"self": 0.0006325679132714868,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025587581330910325,
"count": 8,
"is_parallel": true,
"self": 0.0025587581330910325
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.038901473162695765,
"count": 30,
"is_parallel": true,
"self": 0.007620085380040109,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.031281387782655656,
"count": 120,
"is_parallel": true,
"self": 0.031281387782655656
}
}
},
"UnityEnvironment.step": {
"total": 3725.1082287904574,
"count": 197040,
"is_parallel": true,
"self": 165.97430429654196,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 103.95889578491915,
"count": 197040,
"is_parallel": true,
"self": 103.95889578491915
},
"communicator.exchange": {
"total": 2985.190188732813,
"count": 197040,
"is_parallel": true,
"self": 2985.190188732813
},
"steps_from_proto": {
"total": 469.98483997618314,
"count": 394080,
"is_parallel": true,
"self": 93.58895315986592,
"children": {
"_process_rank_one_or_two_observation": {
"total": 376.3958868163172,
"count": 1576320,
"is_parallel": true,
"self": 376.3958868163172
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1476.3448047513375,
"count": 197041,
"self": 52.264346172101796,
"children": {
"process_trajectory": {
"total": 592.9353361455724,
"count": 197041,
"self": 591.4335409004707,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5017952451016754,
"count": 6,
"self": 1.5017952451016754
}
}
},
"_update_policy": {
"total": 831.1451224336633,
"count": 138,
"self": 504.2810504854424,
"children": {
"TorchPOCAOptimizer.update": {
"total": 326.86407194822095,
"count": 4140,
"self": 326.86407194822095
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.869979314506054e-06,
"count": 1,
"self": 1.869979314506054e-06
},
"TrainerController._save_models": {
"total": 0.25763493101112545,
"count": 1,
"self": 0.0034043260384351015,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25423060497269034,
"count": 1,
"self": 0.25423060497269034
}
}
}
}
}
}
}