Mtc2's picture
First Push
866b718
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0478311777114868,
"min": 1.0478311777114868,
"max": 2.8603241443634033,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10062.322265625,
"min": 10062.322265625,
"max": 29355.505859375,
"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": 12.956374168395996,
"min": 0.3612624406814575,
"max": 13.010994911193848,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2526.492919921875,
"min": 70.08491516113281,
"max": 2654.242919921875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06723006892681559,
"min": 0.06005837692988708,
"max": 0.07531791319203215,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26892027570726235,
"min": 0.24023350771954832,
"max": 0.3765895659601608,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18963708158801584,
"min": 0.11030716639281452,
"max": 0.27909908772391434,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7585483263520634,
"min": 0.44122866557125806,
"max": 1.337033396842433,
"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": 25.204545454545453,
"min": 3.1818181818181817,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 140.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.1818181818181817,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 140.0,
"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": "1690701450",
"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": "1690701923"
},
"total": 472.957867223,
"count": 1,
"self": 0.8399808249999978,
"children": {
"run_training.setup": {
"total": 0.03634319900004357,
"count": 1,
"self": 0.03634319900004357
},
"TrainerController.start_learning": {
"total": 472.08154319899995,
"count": 1,
"self": 0.5549393340073152,
"children": {
"TrainerController._reset_env": {
"total": 5.383992940999974,
"count": 1,
"self": 5.383992940999974
},
"TrainerController.advance": {
"total": 465.90641526199266,
"count": 18222,
"self": 0.2533169689891679,
"children": {
"env_step": {
"total": 465.6530982930035,
"count": 18222,
"self": 337.5456316460045,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.8287801269974,
"count": 18222,
"self": 1.731440716998236,
"children": {
"TorchPolicy.evaluate": {
"total": 126.09733940999917,
"count": 18222,
"self": 126.09733940999917
}
}
},
"workers": {
"total": 0.27868652000159955,
"count": 18222,
"self": 0.0,
"children": {
"worker_root": {
"total": 470.31355188400096,
"count": 18222,
"is_parallel": true,
"self": 220.3526474380127,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005435145999967972,
"count": 1,
"is_parallel": true,
"self": 0.003862771999877168,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015723740000908037,
"count": 10,
"is_parallel": true,
"self": 0.0015723740000908037
}
}
},
"UnityEnvironment.step": {
"total": 0.04305056999999124,
"count": 1,
"is_parallel": true,
"self": 0.000630064000006314,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042969700001549427,
"count": 1,
"is_parallel": true,
"self": 0.00042969700001549427
},
"communicator.exchange": {
"total": 0.03983783999996149,
"count": 1,
"is_parallel": true,
"self": 0.03983783999996149
},
"steps_from_proto": {
"total": 0.0021529690000079427,
"count": 1,
"is_parallel": true,
"self": 0.0005324899999550325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016204790000529101,
"count": 10,
"is_parallel": true,
"self": 0.0016204790000529101
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 249.96090444598826,
"count": 18221,
"is_parallel": true,
"self": 10.54207049198186,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3009635500073955,
"count": 18221,
"is_parallel": true,
"self": 5.3009635500073955
},
"communicator.exchange": {
"total": 198.97692846200346,
"count": 18221,
"is_parallel": true,
"self": 198.97692846200346
},
"steps_from_proto": {
"total": 35.14094194199555,
"count": 18221,
"is_parallel": true,
"self": 6.485499957999025,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.655441983996525,
"count": 182210,
"is_parallel": true,
"self": 28.655441983996525
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001687379999566474,
"count": 1,
"self": 0.0001687379999566474,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.3499443650208,
"count": 440946,
"is_parallel": true,
"self": 9.898638241021047,
"children": {
"process_trajectory": {
"total": 253.7852471379992,
"count": 440946,
"is_parallel": true,
"self": 252.0769136179992,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7083335199999965,
"count": 4,
"is_parallel": true,
"self": 1.7083335199999965
}
}
},
"_update_policy": {
"total": 198.66605898600056,
"count": 90,
"is_parallel": true,
"self": 74.40057376600151,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.26548521999905,
"count": 4587,
"is_parallel": true,
"self": 124.26548521999905
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23602692400004344,
"count": 1,
"self": 0.0011793660000876116,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23484755799995582,
"count": 1,
"self": 0.23484755799995582
}
}
}
}
}
}
}