rodrigoclira's picture
First Push snowball target
0c7f052
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0944734811782837,
"min": 1.0944734811782837,
"max": 2.869121551513672,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10474.111328125,
"min": 10474.111328125,
"max": 29508.9140625,
"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": 12.011147499084473,
"min": 0.39785036444664,
"max": 12.011147499084473,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2342.173828125,
"min": 77.18296813964844,
"max": 2396.458984375,
"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": 0.06696779934424615,
"min": 0.06126919315697616,
"max": 0.07695989694143017,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2678711973769846,
"min": 0.24507677262790464,
"max": 0.38479948470715086,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18600375658156826,
"min": 0.13142617884224428,
"max": 0.267899989380556,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.744015026326273,
"min": 0.5257047153689771,
"max": 1.33949994690278,
"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": 24.022727272727273,
"min": 3.659090909090909,
"max": 24.022727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1057.0,
"min": 161.0,
"max": 1292.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.022727272727273,
"min": 3.659090909090909,
"max": 24.022727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1057.0,
"min": 161.0,
"max": 1292.0,
"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": "1687730340",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "1687730821"
},
"total": 480.6307593459999,
"count": 1,
"self": 0.7804716569999073,
"children": {
"run_training.setup": {
"total": 0.06807017300002371,
"count": 1,
"self": 0.06807017300002371
},
"TrainerController.start_learning": {
"total": 479.78221751599995,
"count": 1,
"self": 0.5839709120051566,
"children": {
"TrainerController._reset_env": {
"total": 5.951863483000011,
"count": 1,
"self": 5.951863483000011
},
"TrainerController.advance": {
"total": 473.0260889589947,
"count": 18211,
"self": 0.2699841369964133,
"children": {
"env_step": {
"total": 472.7561048219983,
"count": 18211,
"self": 341.8526246539768,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.61306534200617,
"count": 18211,
"self": 1.9939526360107038,
"children": {
"TorchPolicy.evaluate": {
"total": 128.61911270599546,
"count": 18211,
"self": 128.61911270599546
}
}
},
"workers": {
"total": 0.2904148260153079,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 477.99558613800343,
"count": 18211,
"is_parallel": true,
"self": 223.44603519199939,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.013528450999956476,
"count": 1,
"is_parallel": true,
"self": 0.004500476999851344,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.009027974000105132,
"count": 10,
"is_parallel": true,
"self": 0.009027974000105132
}
}
},
"UnityEnvironment.step": {
"total": 0.08542172700003903,
"count": 1,
"is_parallel": true,
"self": 0.0006078240000988444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038129400002162583,
"count": 1,
"is_parallel": true,
"self": 0.00038129400002162583
},
"communicator.exchange": {
"total": 0.08240686099998129,
"count": 1,
"is_parallel": true,
"self": 0.08240686099998129
},
"steps_from_proto": {
"total": 0.0020257479999372663,
"count": 1,
"is_parallel": true,
"self": 0.0003672829997185545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016584650002187118,
"count": 10,
"is_parallel": true,
"self": 0.0016584650002187118
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.54955094600405,
"count": 18210,
"is_parallel": true,
"self": 10.681082521002054,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.375614865004877,
"count": 18210,
"is_parallel": true,
"self": 5.375614865004877
},
"communicator.exchange": {
"total": 202.7582448149965,
"count": 18210,
"is_parallel": true,
"self": 202.7582448149965
},
"steps_from_proto": {
"total": 35.73460874500063,
"count": 18210,
"is_parallel": true,
"self": 6.551928003042235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.182680741958393,
"count": 182100,
"is_parallel": true,
"self": 29.182680741958393
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013308200004757964,
"count": 1,
"self": 0.00013308200004757964,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 469.31436150803063,
"count": 469353,
"is_parallel": true,
"self": 10.201973686008955,
"children": {
"process_trajectory": {
"total": 259.68550357202184,
"count": 469353,
"is_parallel": true,
"self": 258.3701616720216,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3153419000002486,
"count": 4,
"is_parallel": true,
"self": 1.3153419000002486
}
}
},
"_update_policy": {
"total": 199.42688424999983,
"count": 90,
"is_parallel": true,
"self": 71.3242237309978,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.10266051900203,
"count": 4587,
"is_parallel": true,
"self": 128.10266051900203
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22016108000002532,
"count": 1,
"self": 0.001049629999897661,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21911145000012766,
"count": 1,
"self": 0.21911145000012766
}
}
}
}
}
}
}