dnarqq's picture
First Push
26e7382
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.201830267906189,
"min": 1.201830267906189,
"max": 2.8562400341033936,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11488.2958984375,
"min": 11488.2958984375,
"max": 29219.3359375,
"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": 11.52927017211914,
"min": 0.4206535816192627,
"max": 11.52927017211914,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2248.207763671875,
"min": 81.60679626464844,
"max": 2332.526611328125,
"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": 0.06548677235624899,
"min": 0.054594234115154225,
"max": 0.07252534857858943,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26194708942499595,
"min": 0.2183769364606169,
"max": 0.35177952828862724,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2339608728447381,
"min": 0.1202103855332597,
"max": 0.2878924263458626,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9358434913789524,
"min": 0.4808415421330388,
"max": 1.3840704215507882,
"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": 23.068181818181817,
"min": 3.272727272727273,
"max": 23.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1015.0,
"min": 144.0,
"max": 1261.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.068181818181817,
"min": 3.272727272727273,
"max": 23.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1015.0,
"min": 144.0,
"max": 1261.0,
"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": "1690103386",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690103856"
},
"total": 470.36718970900006,
"count": 1,
"self": 0.43968837900001745,
"children": {
"run_training.setup": {
"total": 0.033959666999976434,
"count": 1,
"self": 0.033959666999976434
},
"TrainerController.start_learning": {
"total": 469.89354166300006,
"count": 1,
"self": 0.5228472699897679,
"children": {
"TrainerController._reset_env": {
"total": 5.242788806999954,
"count": 1,
"self": 5.242788806999954
},
"TrainerController.advance": {
"total": 463.9873068670104,
"count": 18201,
"self": 0.24764917401336106,
"children": {
"env_step": {
"total": 463.739657692997,
"count": 18201,
"self": 338.0245506659985,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.44856417100516,
"count": 18201,
"self": 1.9226846300154534,
"children": {
"TorchPolicy.evaluate": {
"total": 123.5258795409897,
"count": 18201,
"self": 123.5258795409897
}
}
},
"workers": {
"total": 0.26654285599335026,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.31343133199164,
"count": 18201,
"is_parallel": true,
"self": 221.80081696098927,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004907355999989704,
"count": 1,
"is_parallel": true,
"self": 0.003243627999893306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016637280000963983,
"count": 10,
"is_parallel": true,
"self": 0.0016637280000963983
}
}
},
"UnityEnvironment.step": {
"total": 0.03608636500001694,
"count": 1,
"is_parallel": true,
"self": 0.0006269090000046162,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003165070000363812,
"count": 1,
"is_parallel": true,
"self": 0.0003165070000363812
},
"communicator.exchange": {
"total": 0.032870314999968286,
"count": 1,
"is_parallel": true,
"self": 0.032870314999968286
},
"steps_from_proto": {
"total": 0.002272634000007656,
"count": 1,
"is_parallel": true,
"self": 0.0004537930000196866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018188409999879696,
"count": 10,
"is_parallel": true,
"self": 0.0018188409999879696
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 246.51261437100237,
"count": 18200,
"is_parallel": true,
"self": 10.537890343006438,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.332278528998813,
"count": 18200,
"is_parallel": true,
"self": 5.332278528998813
},
"communicator.exchange": {
"total": 195.79149822100248,
"count": 18200,
"is_parallel": true,
"self": 195.79149822100248
},
"steps_from_proto": {
"total": 34.850947277994635,
"count": 18200,
"is_parallel": true,
"self": 6.434016583988637,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.416930694006,
"count": 182000,
"is_parallel": true,
"self": 28.416930694006
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013868899998215056,
"count": 1,
"self": 0.00013868899998215056,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 460.19861447798024,
"count": 427564,
"is_parallel": true,
"self": 9.832696720988054,
"children": {
"process_trajectory": {
"total": 250.7502290629928,
"count": 427564,
"is_parallel": true,
"self": 249.64851435599292,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1017147069998714,
"count": 4,
"is_parallel": true,
"self": 1.1017147069998714
}
}
},
"_update_policy": {
"total": 199.6156886939994,
"count": 90,
"is_parallel": true,
"self": 81.47927628799806,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.13641240600134,
"count": 4587,
"is_parallel": true,
"self": 118.13641240600134
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14046002999998564,
"count": 1,
"self": 0.0008590639999965788,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13960096599998906,
"count": 1,
"self": 0.13960096599998906
}
}
}
}
}
}
}