WIS's picture
First Push
79e18f0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8784781694412231,
"min": 0.8784781694412231,
"max": 2.8631019592285156,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8397.373046875,
"min": 8397.373046875,
"max": 29321.02734375,
"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": 12.880406379699707,
"min": 0.3703018128871918,
"max": 12.932066917419434,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2511.67919921875,
"min": 71.83855438232422,
"max": 2638.1416015625,
"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": 0.07622303657598084,
"min": 0.06470097742781303,
"max": 0.07786808508407214,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30489214630392336,
"min": 0.2588039097112521,
"max": 0.3836505438935003,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19853914719001917,
"min": 0.13254915858052818,
"max": 0.28686492585157064,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7941565887600767,
"min": 0.5301966343221127,
"max": 1.4343246292578533,
"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": 25.40909090909091,
"min": 3.75,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 165.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.75,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 165.0,
"max": 1406.0,
"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": "1699228400",
"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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699228884"
},
"total": 484.332808701,
"count": 1,
"self": 0.4320447289999265,
"children": {
"run_training.setup": {
"total": 0.0539396400000669,
"count": 1,
"self": 0.0539396400000669
},
"TrainerController.start_learning": {
"total": 483.846824332,
"count": 1,
"self": 0.6053543620032542,
"children": {
"TrainerController._reset_env": {
"total": 8.271964369000102,
"count": 1,
"self": 8.271964369000102
},
"TrainerController.advance": {
"total": 474.87979380899674,
"count": 18200,
"self": 0.29437104400426506,
"children": {
"env_step": {
"total": 474.5854227649925,
"count": 18200,
"self": 325.31987452001147,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.954007913993,
"count": 18200,
"self": 1.5012871560147687,
"children": {
"TorchPolicy.evaluate": {
"total": 147.45272075797823,
"count": 18200,
"self": 147.45272075797823
}
}
},
"workers": {
"total": 0.3115403309880094,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.47033057499016,
"count": 18200,
"is_parallel": true,
"self": 234.65538253299542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0049195499999541425,
"count": 1,
"is_parallel": true,
"self": 0.0033746579998705784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015448920000835642,
"count": 10,
"is_parallel": true,
"self": 0.0015448920000835642
}
}
},
"UnityEnvironment.step": {
"total": 0.038985028999945825,
"count": 1,
"is_parallel": true,
"self": 0.0004272479999372081,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004435580000290429,
"count": 1,
"is_parallel": true,
"self": 0.0004435580000290429
},
"communicator.exchange": {
"total": 0.036008748999961426,
"count": 1,
"is_parallel": true,
"self": 0.036008748999961426
},
"steps_from_proto": {
"total": 0.0021054740000181482,
"count": 1,
"is_parallel": true,
"self": 0.0004083909998371382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00169708300018101,
"count": 10,
"is_parallel": true,
"self": 0.00169708300018101
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.81494804199474,
"count": 18199,
"is_parallel": true,
"self": 10.829699535004352,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.553929744006837,
"count": 18199,
"is_parallel": true,
"self": 5.553929744006837
},
"communicator.exchange": {
"total": 195.7406785309896,
"count": 18199,
"is_parallel": true,
"self": 195.7406785309896
},
"steps_from_proto": {
"total": 35.69064023199394,
"count": 18199,
"is_parallel": true,
"self": 6.851532123960055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.839108108033884,
"count": 181990,
"is_parallel": true,
"self": 28.839108108033884
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001249249999091262,
"count": 1,
"self": 0.0001249249999091262,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 471.0960512179415,
"count": 482545,
"is_parallel": true,
"self": 10.45036259597714,
"children": {
"process_trajectory": {
"total": 267.3544899219637,
"count": 482545,
"is_parallel": true,
"self": 266.5654638199635,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7890261020002072,
"count": 4,
"is_parallel": true,
"self": 0.7890261020002072
}
}
},
"_update_policy": {
"total": 193.29119870000068,
"count": 90,
"is_parallel": true,
"self": 58.54208629599907,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.7491124040016,
"count": 4584,
"is_parallel": true,
"self": 134.7491124040016
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08958686699997997,
"count": 1,
"self": 0.0008798090000254888,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08870705799995449,
"count": 1,
"self": 0.08870705799995449
}
}
}
}
}
}
}