eliotz's picture
First Push
ff3da0c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1299118995666504,
"min": 1.1299118995666504,
"max": 2.8659093379974365,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10788.3984375,
"min": 10788.3984375,
"max": 29349.77734375,
"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": 11.859926223754883,
"min": 0.42619091272354126,
"max": 11.859926223754883,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2312.685546875,
"min": 82.68103790283203,
"max": 2395.361328125,
"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": 0.06591661130397708,
"min": 0.060527617515831744,
"max": 0.07487757971770513,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2636664452159083,
"min": 0.2473542906832425,
"max": 0.37438789858852567,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2116368612384095,
"min": 0.12127370242481395,
"max": 0.2826047219482123,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.846547444953638,
"min": 0.4850948096992558,
"max": 1.4130236097410613,
"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": 23.65909090909091,
"min": 3.522727272727273,
"max": 23.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1041.0,
"min": 155.0,
"max": 1264.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.65909090909091,
"min": 3.522727272727273,
"max": 23.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1041.0,
"min": 155.0,
"max": 1264.0,
"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": "1673410239",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673410700"
},
"total": 461.570559178,
"count": 1,
"self": 0.4382925160000468,
"children": {
"run_training.setup": {
"total": 0.13471521200000325,
"count": 1,
"self": 0.13471521200000325
},
"TrainerController.start_learning": {
"total": 460.99755144999995,
"count": 1,
"self": 0.5762464940034988,
"children": {
"TrainerController._reset_env": {
"total": 7.1760388469999725,
"count": 1,
"self": 7.1760388469999725
},
"TrainerController.advance": {
"total": 453.1153170909964,
"count": 18201,
"self": 0.28439588799625426,
"children": {
"env_step": {
"total": 452.8309212030002,
"count": 18201,
"self": 298.7950021660115,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.7434057649918,
"count": 18201,
"self": 1.5009517159834331,
"children": {
"TorchPolicy.evaluate": {
"total": 152.24245404900836,
"count": 18201,
"self": 34.763809307001054,
"children": {
"TorchPolicy.sample_actions": {
"total": 117.4786447420073,
"count": 18201,
"self": 117.4786447420073
}
}
}
}
},
"workers": {
"total": 0.2925132719968815,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 459.6594417160038,
"count": 18201,
"is_parallel": true,
"self": 219.77977592000877,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008960423000019091,
"count": 1,
"is_parallel": true,
"self": 0.004089087000068048,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004871335999951043,
"count": 10,
"is_parallel": true,
"self": 0.004871335999951043
}
}
},
"UnityEnvironment.step": {
"total": 0.042901336999989326,
"count": 1,
"is_parallel": true,
"self": 0.00047568799999453404,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003076410000062424,
"count": 1,
"is_parallel": true,
"self": 0.0003076410000062424
},
"communicator.exchange": {
"total": 0.040028097999993406,
"count": 1,
"is_parallel": true,
"self": 0.040028097999993406
},
"steps_from_proto": {
"total": 0.002089909999995143,
"count": 1,
"is_parallel": true,
"self": 0.0005831330001342394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015067769998609037,
"count": 10,
"is_parallel": true,
"self": 0.0015067769998609037
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.87966579599504,
"count": 18200,
"is_parallel": true,
"self": 9.100485902993796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.372767535004186,
"count": 18200,
"is_parallel": true,
"self": 5.372767535004186
},
"communicator.exchange": {
"total": 192.76277366199548,
"count": 18200,
"is_parallel": true,
"self": 192.76277366199548
},
"steps_from_proto": {
"total": 32.643638696001574,
"count": 18200,
"is_parallel": true,
"self": 7.166487159032272,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.477151536969302,
"count": 182000,
"is_parallel": true,
"self": 25.477151536969302
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.001700003504084e-05,
"count": 1,
"self": 5.001700003504084e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 449.9729107590411,
"count": 360802,
"is_parallel": true,
"self": 9.571092258034014,
"children": {
"process_trajectory": {
"total": 256.0303102450071,
"count": 360802,
"is_parallel": true,
"self": 255.18958719600727,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8407230489998483,
"count": 4,
"is_parallel": true,
"self": 0.8407230489998483
}
}
},
"_update_policy": {
"total": 184.37150825599997,
"count": 90,
"is_parallel": true,
"self": 49.92815699200105,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.44335126399892,
"count": 4587,
"is_parallel": true,
"self": 134.44335126399892
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1298990010000125,
"count": 1,
"self": 0.000947195999970063,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12895180500004244,
"count": 1,
"self": 0.12895180500004244
}
}
}
}
}
}
}