palushok's picture
First Push
c22ebf4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9066334366798401,
"min": 0.8926143050193787,
"max": 2.871134042739868,
"count": 17
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8696.427734375,
"min": 8696.427734375,
"max": 29308.537109375,
"count": 17
},
"SnowballTarget.Step.mean": {
"value": 169976.0,
"min": 9952.0,
"max": 169976.0,
"count": 17
},
"SnowballTarget.Step.sum": {
"value": 169976.0,
"min": 9952.0,
"max": 169976.0,
"count": 17
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.58845043182373,
"min": 0.30016788840293884,
"max": 12.58845043182373,
"count": 17
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2580.63232421875,
"min": 58.23257064819336,
"max": 2580.63232421875,
"count": 17
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06821819086172207,
"min": 0.0623733314469242,
"max": 0.07623494047355979,
"count": 17
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.34109095430861036,
"min": 0.2494933257876968,
"max": 0.3634344751149982,
"count": 17
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20577162515883352,
"min": 0.10238019711858429,
"max": 0.29640629449311423,
"count": 17
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0288581257941676,
"min": 0.40952078847433715,
"max": 1.4820314724655712,
"count": 17
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.263208245600001e-05,
"min": 5.263208245600001e-05,
"max": 0.000291882002706,
"count": 17
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00026316041228000004,
"min": 0.00026316041228000004,
"max": 0.00138516003828,
"count": 17
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.11754400000000001,
"min": 0.11754400000000001,
"max": 0.19729400000000002,
"count": 17
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.58772,
"min": 0.4899760000000001,
"max": 0.96172,
"count": 17
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0008854456000000002,
"min": 0.0008854456000000002,
"max": 0.0048649706,
"count": 17
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.004427228000000001,
"min": 0.004427228000000001,
"max": 0.023089828,
"count": 17
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 17
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 17
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.490909090909092,
"min": 2.8636363636363638,
"max": 25.490909090909092,
"count": 17
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1402.0,
"min": 126.0,
"max": 1402.0,
"count": 17
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.490909090909092,
"min": 2.8636363636363638,
"max": 25.490909090909092,
"count": 17
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1402.0,
"min": 126.0,
"max": 1402.0,
"count": 17
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 17
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 17
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1743363690",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743364081"
},
"total": 390.981760366,
"count": 1,
"self": 0.3007936559999962,
"children": {
"run_training.setup": {
"total": 0.03400451200002408,
"count": 1,
"self": 0.03400451200002408
},
"TrainerController.start_learning": {
"total": 390.646962198,
"count": 1,
"self": 0.3452465139959031,
"children": {
"TrainerController._reset_env": {
"total": 3.424280672000009,
"count": 1,
"self": 3.424280672000009
},
"TrainerController.advance": {
"total": 386.7368774560041,
"count": 15657,
"self": 0.3626876060045561,
"children": {
"env_step": {
"total": 276.79026723399704,
"count": 15657,
"self": 210.7636918539988,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.82985719399619,
"count": 15657,
"self": 1.2013860589959222,
"children": {
"TorchPolicy.evaluate": {
"total": 64.62847113500027,
"count": 15657,
"self": 64.62847113500027
}
}
},
"workers": {
"total": 0.1967181860020446,
"count": 15656,
"self": 0.0,
"children": {
"worker_root": {
"total": 389.4681249269951,
"count": 15656,
"is_parallel": true,
"self": 204.63124143800405,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006203246999916701,
"count": 1,
"is_parallel": true,
"self": 0.004104943999777788,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020983030001389125,
"count": 10,
"is_parallel": true,
"self": 0.0020983030001389125
}
}
},
"UnityEnvironment.step": {
"total": 0.04036295799994605,
"count": 1,
"is_parallel": true,
"self": 0.0007071669999731967,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041874999999436113,
"count": 1,
"is_parallel": true,
"self": 0.00041874999999436113
},
"communicator.exchange": {
"total": 0.03715855400002965,
"count": 1,
"is_parallel": true,
"self": 0.03715855400002965
},
"steps_from_proto": {
"total": 0.0020784869999488365,
"count": 1,
"is_parallel": true,
"self": 0.0005132190000267656,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015652679999220709,
"count": 10,
"is_parallel": true,
"self": 0.0015652679999220709
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 184.83688348899102,
"count": 15655,
"is_parallel": true,
"self": 8.78840796098359,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.9131978479992995,
"count": 15655,
"is_parallel": true,
"self": 4.9131978479992995
},
"communicator.exchange": {
"total": 142.08874353399983,
"count": 15655,
"is_parallel": true,
"self": 142.08874353399983
},
"steps_from_proto": {
"total": 29.046534146008298,
"count": 15655,
"is_parallel": true,
"self": 5.292675785033339,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.75385836097496,
"count": 156550,
"is_parallel": true,
"self": 23.75385836097496
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 109.5839226160025,
"count": 15656,
"self": 0.4289593530041884,
"children": {
"process_trajectory": {
"total": 24.60215235499811,
"count": 15656,
"self": 24.140989672998103,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4611626820000083,
"count": 3,
"self": 0.4611626820000083
}
}
},
"_update_policy": {
"total": 84.5528109080002,
"count": 78,
"self": 33.713068504998546,
"children": {
"TorchPPOOptimizer.update": {
"total": 50.83974240300165,
"count": 3975,
"self": 50.83974240300165
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3850000186721445e-06,
"count": 1,
"self": 1.3850000186721445e-06
},
"TrainerController._save_models": {
"total": 0.14055617099995743,
"count": 1,
"self": 0.0012240159999237221,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1393321550000337,
"count": 1,
"self": 0.1393321550000337
}
}
}
}
}
}
}