Uxinnn's picture
First Push
049492a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8756385445594788,
"min": 0.8681148886680603,
"max": 2.8697896003723145,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8360.5966796875,
"min": 8360.5966796875,
"max": 29421.083984375,
"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": 12.944748878479004,
"min": 0.3184618055820465,
"max": 12.944748878479004,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.22607421875,
"min": 61.78158950805664,
"max": 2612.40576171875,
"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": 0.06581517658680462,
"min": 0.06439895621310023,
"max": 0.07988098732517648,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2632607063472185,
"min": 0.2575958248524009,
"max": 0.39940493662588245,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1817477529534709,
"min": 0.11408543325138881,
"max": 0.28933293160562423,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7269910118138836,
"min": 0.45634173300555525,
"max": 1.428839938678578,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.130097290000004e-06,
"min": 8.130097290000004e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2520389160000015e-05,
"min": 3.2520389160000015e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10271,
"min": 0.10271,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41084,
"min": 0.41084,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014522900000000008,
"min": 0.00014522900000000008,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005809160000000003,
"min": 0.0005809160000000003,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.454545454545453,
"min": 3.090909090909091,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 136.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.090909090909091,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 136.0,
"max": 1404.0,
"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": "1685980201",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./content/ml-agents/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": "1685980642"
},
"total": 441.06050001100004,
"count": 1,
"self": 0.44173997299992607,
"children": {
"run_training.setup": {
"total": 0.04626687500001481,
"count": 1,
"self": 0.04626687500001481
},
"TrainerController.start_learning": {
"total": 440.5724931630001,
"count": 1,
"self": 0.4925370699972973,
"children": {
"TrainerController._reset_env": {
"total": 3.731544113000041,
"count": 1,
"self": 3.731544113000041
},
"TrainerController.advance": {
"total": 436.2189979480029,
"count": 18201,
"self": 0.23838751500511535,
"children": {
"env_step": {
"total": 435.98061043299776,
"count": 18201,
"self": 317.4438694430022,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.28934619699635,
"count": 18201,
"self": 1.6925609299971711,
"children": {
"TorchPolicy.evaluate": {
"total": 116.59678526699918,
"count": 18201,
"self": 116.59678526699918
}
}
},
"workers": {
"total": 0.2473947929992164,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 439.0531513680048,
"count": 18201,
"is_parallel": true,
"self": 206.69713702301146,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005762562999962029,
"count": 1,
"is_parallel": true,
"self": 0.004350002000023778,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014125609999382505,
"count": 10,
"is_parallel": true,
"self": 0.0014125609999382505
}
}
},
"UnityEnvironment.step": {
"total": 0.0452404170000591,
"count": 1,
"is_parallel": true,
"self": 0.0005511409999598982,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032626100005472836,
"count": 1,
"is_parallel": true,
"self": 0.00032626100005472836
},
"communicator.exchange": {
"total": 0.04238379800005987,
"count": 1,
"is_parallel": true,
"self": 0.04238379800005987
},
"steps_from_proto": {
"total": 0.001979216999984601,
"count": 1,
"is_parallel": true,
"self": 0.0003689710000571722,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016102459999274288,
"count": 10,
"is_parallel": true,
"self": 0.0016102459999274288
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.35601434499335,
"count": 18200,
"is_parallel": true,
"self": 9.229677151003102,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.017728726007249,
"count": 18200,
"is_parallel": true,
"self": 5.017728726007249
},
"communicator.exchange": {
"total": 186.72167467998702,
"count": 18200,
"is_parallel": true,
"self": 186.72167467998702
},
"steps_from_proto": {
"total": 31.386933787995986,
"count": 18200,
"is_parallel": true,
"self": 5.908998708010131,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.477935079985855,
"count": 182000,
"is_parallel": true,
"self": 25.477935079985855
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015713199991296278,
"count": 1,
"self": 0.00015713199991296278,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 432.96654051500286,
"count": 411329,
"is_parallel": true,
"self": 8.957942946976914,
"children": {
"process_trajectory": {
"total": 235.53511822302528,
"count": 411329,
"is_parallel": true,
"self": 234.03791702402498,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4972011990003011,
"count": 4,
"is_parallel": true,
"self": 1.4972011990003011
}
}
},
"_update_policy": {
"total": 188.47347934500067,
"count": 90,
"is_parallel": true,
"self": 71.79579744899945,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.67768189600122,
"count": 4584,
"is_parallel": true,
"self": 116.67768189600122
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12925689999997303,
"count": 1,
"self": 0.0009031060001234437,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12835379399984959,
"count": 1,
"self": 0.12835379399984959
}
}
}
}
}
}
}