PierreCounathe's picture
First Push
8f15c91 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8526651263237,
"min": 0.8526651263237,
"max": 2.872190475463867,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8141.24658203125,
"min": 8141.24658203125,
"max": 29414.1015625,
"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": 12.739330291748047,
"min": 0.21190494298934937,
"max": 12.739330291748047,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2484.16943359375,
"min": 41.10955810546875,
"max": 2583.023193359375,
"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": 0.061868697761508204,
"min": 0.06041482629549208,
"max": 0.07658735018362765,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24747479104603282,
"min": 0.24165930518196832,
"max": 0.3644466401926954,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20337878547006233,
"min": 0.10687985088374903,
"max": 0.2931369316344168,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8135151418802493,
"min": 0.4275194035349961,
"max": 1.465684658172084,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.106097298000005e-06,
"min": 8.106097298000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.242438919200002e-05,
"min": 3.242438919200002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10270200000000002,
"min": 0.10270200000000002,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41080800000000006,
"min": 0.41080800000000006,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001448298000000001,
"min": 0.0001448298000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005793192000000004,
"min": 0.0005793192000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.454545454545453,
"min": 3.159090909090909,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 139.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.159090909090909,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 139.0,
"max": 1388.0,
"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": "1707533615",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707534072"
},
"total": 456.587898301,
"count": 1,
"self": 0.43973006000010173,
"children": {
"run_training.setup": {
"total": 0.05446885599997131,
"count": 1,
"self": 0.05446885599997131
},
"TrainerController.start_learning": {
"total": 456.0936993849999,
"count": 1,
"self": 0.6073641830073484,
"children": {
"TrainerController._reset_env": {
"total": 2.9656644210000422,
"count": 1,
"self": 2.9656644210000422
},
"TrainerController.advance": {
"total": 452.4284576409923,
"count": 18199,
"self": 0.30112849599493074,
"children": {
"env_step": {
"total": 452.12732914499736,
"count": 18199,
"self": 290.9262691630099,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.89739892499347,
"count": 18199,
"self": 1.522227701991369,
"children": {
"TorchPolicy.evaluate": {
"total": 159.3751712230021,
"count": 18199,
"self": 159.3751712230021
}
}
},
"workers": {
"total": 0.30366105699397394,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.959741318999,
"count": 18199,
"is_parallel": true,
"self": 227.3599911010059,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005817662000026758,
"count": 1,
"is_parallel": true,
"self": 0.004203373999871474,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001614288000155284,
"count": 10,
"is_parallel": true,
"self": 0.001614288000155284
}
}
},
"UnityEnvironment.step": {
"total": 0.042543447000070955,
"count": 1,
"is_parallel": true,
"self": 0.0007712530001526829,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004423799999813127,
"count": 1,
"is_parallel": true,
"self": 0.0004423799999813127
},
"communicator.exchange": {
"total": 0.03900783199992475,
"count": 1,
"is_parallel": true,
"self": 0.03900783199992475
},
"steps_from_proto": {
"total": 0.0023219820000122127,
"count": 1,
"is_parallel": true,
"self": 0.0005903499999249107,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001731632000087302,
"count": 10,
"is_parallel": true,
"self": 0.001731632000087302
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.59975021799312,
"count": 18198,
"is_parallel": true,
"self": 10.790377073978107,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.757217063003168,
"count": 18198,
"is_parallel": true,
"self": 5.757217063003168
},
"communicator.exchange": {
"total": 175.71877328400433,
"count": 18198,
"is_parallel": true,
"self": 175.71877328400433
},
"steps_from_proto": {
"total": 35.333382797007516,
"count": 18198,
"is_parallel": true,
"self": 6.6715656590014305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.661817138006086,
"count": 181980,
"is_parallel": true,
"self": 28.661817138006086
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015667400020902278,
"count": 1,
"self": 0.00015667400020902278,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 446.4875763619856,
"count": 699217,
"is_parallel": true,
"self": 15.141761271927635,
"children": {
"process_trajectory": {
"total": 244.65340317005837,
"count": 699217,
"is_parallel": true,
"self": 244.11292728005833,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5404758900000388,
"count": 4,
"is_parallel": true,
"self": 0.5404758900000388
}
}
},
"_update_policy": {
"total": 186.69241191999959,
"count": 90,
"is_parallel": true,
"self": 53.63571222499627,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.05669969500332,
"count": 4584,
"is_parallel": true,
"self": 133.05669969500332
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09205646600003092,
"count": 1,
"self": 0.0009546979999868199,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0911017680000441,
"count": 1,
"self": 0.0911017680000441
}
}
}
}
}
}
}