davera-017's picture
First Push
6a71ab5
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9595863819122314,
"min": 0.959284245967865,
"max": 2.865565776824951,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9162.130859375,
"min": 9162.130859375,
"max": 29314.73828125,
"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": 12.684906959533691,
"min": 0.3475661873817444,
"max": 12.684906959533691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2473.556884765625,
"min": 67.42784118652344,
"max": 2569.567626953125,
"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": 0.06952865240529327,
"min": 0.06135435927724615,
"max": 0.08289780059792118,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27811460962117307,
"min": 0.2454174371089846,
"max": 0.3688318996516732,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19938386480013529,
"min": 0.11854352080491463,
"max": 0.31541242839074607,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7975354592005411,
"min": 0.47417408321965854,
"max": 1.5770621419537303,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"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": 0.96172,
"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": 24.704545454545453,
"min": 3.272727272727273,
"max": 25.10909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1087.0,
"min": 144.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.704545454545453,
"min": 3.272727272727273,
"max": 25.10909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1087.0,
"min": 144.0,
"max": 1381.0,
"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": "1693505796",
"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": "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": "1693506281"
},
"total": 485.7702353500001,
"count": 1,
"self": 0.4318896060001407,
"children": {
"run_training.setup": {
"total": 0.043245704000014484,
"count": 1,
"self": 0.043245704000014484
},
"TrainerController.start_learning": {
"total": 485.29510003999997,
"count": 1,
"self": 0.5635086810045777,
"children": {
"TrainerController._reset_env": {
"total": 5.112926690999984,
"count": 1,
"self": 5.112926690999984
},
"TrainerController.advance": {
"total": 479.47552521899536,
"count": 18202,
"self": 0.27649909700198805,
"children": {
"env_step": {
"total": 479.19902612199337,
"count": 18202,
"self": 350.7521669189932,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.16407084299738,
"count": 18202,
"self": 1.8469539260032661,
"children": {
"TorchPolicy.evaluate": {
"total": 126.31711691699411,
"count": 18202,
"self": 126.31711691699411
}
}
},
"workers": {
"total": 0.28278836000276897,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 483.5679305330011,
"count": 18202,
"is_parallel": true,
"self": 228.45603853000762,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004595666999989589,
"count": 1,
"is_parallel": true,
"self": 0.003153274999817768,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014423920001718216,
"count": 10,
"is_parallel": true,
"self": 0.0014423920001718216
}
}
},
"UnityEnvironment.step": {
"total": 0.10433678399999735,
"count": 1,
"is_parallel": true,
"self": 0.0007018999999672815,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004048399999874164,
"count": 1,
"is_parallel": true,
"self": 0.0004048399999874164
},
"communicator.exchange": {
"total": 0.10060270400003901,
"count": 1,
"is_parallel": true,
"self": 0.10060270400003901
},
"steps_from_proto": {
"total": 0.0026273400000036418,
"count": 1,
"is_parallel": true,
"self": 0.0008666100001164523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017607299998871895,
"count": 10,
"is_parallel": true,
"self": 0.0017607299998871895
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.1118920029935,
"count": 18201,
"is_parallel": true,
"self": 10.7492848509969,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.370988146995501,
"count": 18201,
"is_parallel": true,
"self": 5.370988146995501
},
"communicator.exchange": {
"total": 202.16730842299057,
"count": 18201,
"is_parallel": true,
"self": 202.16730842299057
},
"steps_from_proto": {
"total": 36.824310582010526,
"count": 18201,
"is_parallel": true,
"self": 6.61731536297907,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.206995219031455,
"count": 182010,
"is_parallel": true,
"self": 30.206995219031455
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020462599991333263,
"count": 1,
"self": 0.00020462599991333263,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 475.69541778896837,
"count": 455619,
"is_parallel": true,
"self": 10.047069688935153,
"children": {
"process_trajectory": {
"total": 260.5048082040338,
"count": 455619,
"is_parallel": true,
"self": 259.18324045003385,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3215677539999433,
"count": 4,
"is_parallel": true,
"self": 1.3215677539999433
}
}
},
"_update_policy": {
"total": 205.14353989599942,
"count": 90,
"is_parallel": true,
"self": 84.98193114299545,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.16160875300397,
"count": 4587,
"is_parallel": true,
"self": 120.16160875300397
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14293482300013238,
"count": 1,
"self": 0.0008733680001569155,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14206145499997547,
"count": 1,
"self": 0.14206145499997547
}
}
}
}
}
}
}