Punit71's picture
First Push
55886e0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9683530330657959,
"min": 0.9683530330657959,
"max": 2.854764223098755,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9245.8349609375,
"min": 9245.8349609375,
"max": 29235.640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.315727233886719,
"min": 0.46386510133743286,
"max": 13.315727233886719,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2596.56689453125,
"min": 89.98983001708984,
"max": 2690.83056640625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06619497080419558,
"min": 0.06539844028905945,
"max": 0.06917121435138944,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2647798832167823,
"min": 0.2615937611562378,
"max": 0.3458560717569472,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18898869063705206,
"min": 0.1378296170695274,
"max": 0.26269716459162096,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7559547625482083,
"min": 0.5513184682781096,
"max": 1.3134858229581048,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382799997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.431818181818183,
"min": 3.977272727272727,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1163.0,
"min": 175.0,
"max": 1437.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.431818181818183,
"min": 3.977272727272727,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1163.0,
"min": 175.0,
"max": 1437.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697064822",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697065473"
},
"total": 650.5086318880001,
"count": 1,
"self": 0.38406461099998523,
"children": {
"run_training.setup": {
"total": 0.04779320700004064,
"count": 1,
"self": 0.04779320700004064
},
"TrainerController.start_learning": {
"total": 650.07677407,
"count": 1,
"self": 0.5380560020005305,
"children": {
"TrainerController._reset_env": {
"total": 7.977807081999913,
"count": 1,
"self": 7.977807081999913
},
"TrainerController.advance": {
"total": 641.4776578719994,
"count": 18201,
"self": 0.26412508699615955,
"children": {
"env_step": {
"total": 641.2135327850033,
"count": 18201,
"self": 500.0749530330131,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.8593828130098,
"count": 18201,
"self": 1.410856081011616,
"children": {
"TorchPolicy.evaluate": {
"total": 139.4485267319982,
"count": 18201,
"self": 139.4485267319982
}
}
},
"workers": {
"total": 0.2791969389803626,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 648.8583593559957,
"count": 18201,
"is_parallel": true,
"self": 409.9084812100125,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053917779999892446,
"count": 1,
"is_parallel": true,
"self": 0.004068091999897661,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001323686000091584,
"count": 10,
"is_parallel": true,
"self": 0.001323686000091584
}
}
},
"UnityEnvironment.step": {
"total": 0.037794344999952045,
"count": 1,
"is_parallel": true,
"self": 0.0006198009998570342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032749700005751947,
"count": 1,
"is_parallel": true,
"self": 0.00032749700005751947
},
"communicator.exchange": {
"total": 0.034992620000025454,
"count": 1,
"is_parallel": true,
"self": 0.034992620000025454
},
"steps_from_proto": {
"total": 0.0018544270000120378,
"count": 1,
"is_parallel": true,
"self": 0.00036709400001200265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001487333000000035,
"count": 10,
"is_parallel": true,
"self": 0.001487333000000035
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.94987814598323,
"count": 18200,
"is_parallel": true,
"self": 10.356057908992739,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.248376847981945,
"count": 18200,
"is_parallel": true,
"self": 5.248376847981945
},
"communicator.exchange": {
"total": 190.31173412799717,
"count": 18200,
"is_parallel": true,
"self": 190.31173412799717
},
"steps_from_proto": {
"total": 33.03370926101138,
"count": 18200,
"is_parallel": true,
"self": 6.114651477967527,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.919057783043854,
"count": 182000,
"is_parallel": true,
"self": 26.919057783043854
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001129150000451773,
"count": 1,
"self": 0.0001129150000451773,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 637.7884814849942,
"count": 486583,
"is_parallel": true,
"self": 9.744187824983442,
"children": {
"process_trajectory": {
"total": 254.72997143901125,
"count": 486583,
"is_parallel": true,
"self": 253.9787212500113,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7512501889999612,
"count": 4,
"is_parallel": true,
"self": 0.7512501889999612
}
}
},
"_update_policy": {
"total": 373.31432222099954,
"count": 90,
"is_parallel": true,
"self": 152.3676457080103,
"children": {
"TorchPPOOptimizer.update": {
"total": 220.94667651298926,
"count": 15280,
"is_parallel": true,
"self": 220.94667651298926
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08314019900012681,
"count": 1,
"self": 0.000818383000250833,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08232181599987598,
"count": 1,
"self": 0.08232181599987598
}
}
}
}
}
}
}