Scrwed's picture
First test training
092ba2f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7948322892189026,
"min": 0.7948322892189026,
"max": 2.833730459213257,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7597.8017578125,
"min": 7597.8017578125,
"max": 29020.234375,
"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": 12.916888236999512,
"min": 0.3813643455505371,
"max": 12.916888236999512,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.793212890625,
"min": 73.98468017578125,
"max": 2618.57080078125,
"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": 0.06719503292982813,
"min": 0.0634634419893629,
"max": 0.07355965919788086,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26878013171931253,
"min": 0.25910620521651306,
"max": 0.36779829598940433,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18446878738263073,
"min": 0.15355738699002483,
"max": 0.2932366422578401,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7378751495305229,
"min": 0.6142295479600993,
"max": 1.4661832112892004,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.616409730600001e-05,
"min": 1.616409730600001e-05,
"max": 0.0005837640027059999,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 6.465638922400003e-05,
"min": 6.465638922400003e-05,
"max": 0.00277032003828,
"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": 4.0227272727272725,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 177.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 4.0227272727272725,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 177.0,
"max": 1399.0,
"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": "1673850944",
"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": "1673851360"
},
"total": 415.7499391939999,
"count": 1,
"self": 0.34932398199998715,
"children": {
"run_training.setup": {
"total": 0.10780421499998738,
"count": 1,
"self": 0.10780421499998738
},
"TrainerController.start_learning": {
"total": 415.29281099699995,
"count": 1,
"self": 0.49743538100096885,
"children": {
"TrainerController._reset_env": {
"total": 9.674402912000005,
"count": 1,
"self": 9.674402912000005
},
"TrainerController.advance": {
"total": 405.00371319299904,
"count": 18201,
"self": 0.24157018901144056,
"children": {
"env_step": {
"total": 404.7621430039876,
"count": 18201,
"self": 263.645355118981,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.8672906270018,
"count": 18201,
"self": 1.3131185599996797,
"children": {
"TorchPolicy.evaluate": {
"total": 139.55417206700213,
"count": 18201,
"self": 30.676380087997472,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.87779197900466,
"count": 18201,
"self": 108.87779197900466
}
}
}
}
},
"workers": {
"total": 0.24949725800479428,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 414.1390265430033,
"count": 18201,
"is_parallel": true,
"self": 201.580090749997,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005842938000000686,
"count": 1,
"is_parallel": true,
"self": 0.0036042450003606064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022386929996400795,
"count": 10,
"is_parallel": true,
"self": 0.0022386929996400795
}
}
},
"UnityEnvironment.step": {
"total": 0.03182448400002613,
"count": 1,
"is_parallel": true,
"self": 0.0005300359999864668,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034926499995435734,
"count": 1,
"is_parallel": true,
"self": 0.00034926499995435734
},
"communicator.exchange": {
"total": 0.02912632400000348,
"count": 1,
"is_parallel": true,
"self": 0.02912632400000348
},
"steps_from_proto": {
"total": 0.0018188590000818294,
"count": 1,
"is_parallel": true,
"self": 0.0004141739999568017,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014046850001250277,
"count": 10,
"is_parallel": true,
"self": 0.0014046850001250277
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.5589357930063,
"count": 18200,
"is_parallel": true,
"self": 8.060201444983704,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.835662035006521,
"count": 18200,
"is_parallel": true,
"self": 4.835662035006521
},
"communicator.exchange": {
"total": 167.7835401220051,
"count": 18200,
"is_parallel": true,
"self": 167.7835401220051
},
"steps_from_proto": {
"total": 31.87953219101098,
"count": 18200,
"is_parallel": true,
"self": 6.3688160410337105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.51071614997727,
"count": 182000,
"is_parallel": true,
"self": 25.51071614997727
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.996199984612758e-05,
"count": 1,
"self": 3.996199984612758e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 402.25809715299226,
"count": 322718,
"is_parallel": true,
"self": 8.696737903016583,
"children": {
"process_trajectory": {
"total": 230.01735275197552,
"count": 322718,
"is_parallel": true,
"self": 229.36983190797548,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6475208440000415,
"count": 4,
"is_parallel": true,
"self": 0.6475208440000415
}
}
},
"_update_policy": {
"total": 163.54400649800016,
"count": 90,
"is_parallel": true,
"self": 43.11903591699877,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.42497058100139,
"count": 4587,
"is_parallel": true,
"self": 120.42497058100139
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11721954900008313,
"count": 1,
"self": 0.000835562000020218,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11638398700006292,
"count": 1,
"self": 0.11638398700006292
}
}
}
}
}
}
}