calvinyz's picture
First Push
c64220e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0324552059173584,
"min": 1.0324552059173584,
"max": 2.866994857788086,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9857.8818359375,
"min": 9857.8818359375,
"max": 29360.89453125,
"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": 12.046711921691895,
"min": 0.43739160895347595,
"max": 12.046711921691895,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2349.10888671875,
"min": 84.85397338867188,
"max": 2454.455078125,
"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": 0.07184399524817754,
"min": 0.0647767149759602,
"max": 0.07327421285384951,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28737598099271017,
"min": 0.25991522327896355,
"max": 0.36333089538989133,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18653757402709886,
"min": 0.11311274551211253,
"max": 0.29352035008224786,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7461502961083954,
"min": 0.45245098204845013,
"max": 1.4676017504112393,
"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": 23.431818181818183,
"min": 3.1363636363636362,
"max": 23.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1031.0,
"min": 138.0,
"max": 1319.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.431818181818183,
"min": 3.1363636363636362,
"max": 23.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1031.0,
"min": 138.0,
"max": 1319.0,
"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": "1703883695",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703884152"
},
"total": 457.815165531,
"count": 1,
"self": 0.4446675290000144,
"children": {
"run_training.setup": {
"total": 0.05229980600000772,
"count": 1,
"self": 0.05229980600000772
},
"TrainerController.start_learning": {
"total": 457.31819819599997,
"count": 1,
"self": 0.566433689991527,
"children": {
"TrainerController._reset_env": {
"total": 3.413152911999987,
"count": 1,
"self": 3.413152911999987
},
"TrainerController.advance": {
"total": 453.2388446920085,
"count": 18199,
"self": 0.27509964801458864,
"children": {
"env_step": {
"total": 452.9637450439939,
"count": 18199,
"self": 297.59554888299704,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.08067610900082,
"count": 18199,
"self": 1.5070802770127898,
"children": {
"TorchPolicy.evaluate": {
"total": 153.57359583198803,
"count": 18199,
"self": 153.57359583198803
}
}
},
"workers": {
"total": 0.28752005199606856,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.09806794499934,
"count": 18199,
"is_parallel": true,
"self": 225.10175253799787,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004813803999979882,
"count": 1,
"is_parallel": true,
"self": 0.003510926999979347,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013028770000005352,
"count": 10,
"is_parallel": true,
"self": 0.0013028770000005352
}
}
},
"UnityEnvironment.step": {
"total": 0.06786679399999684,
"count": 1,
"is_parallel": true,
"self": 0.0006597280000164574,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038208199998734926,
"count": 1,
"is_parallel": true,
"self": 0.00038208199998734926
},
"communicator.exchange": {
"total": 0.06500239600001123,
"count": 1,
"is_parallel": true,
"self": 0.06500239600001123
},
"steps_from_proto": {
"total": 0.0018225879999818062,
"count": 1,
"is_parallel": true,
"self": 0.0003505869999571587,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014720010000246475,
"count": 10,
"is_parallel": true,
"self": 0.0014720010000246475
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.99631540700148,
"count": 18198,
"is_parallel": true,
"self": 10.888756725999315,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.617947646005405,
"count": 18198,
"is_parallel": true,
"self": 5.617947646005405
},
"communicator.exchange": {
"total": 179.39953516199841,
"count": 18198,
"is_parallel": true,
"self": 179.39953516199841
},
"steps_from_proto": {
"total": 35.09007587299834,
"count": 18198,
"is_parallel": true,
"self": 6.573846049979693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.516229823018648,
"count": 181980,
"is_parallel": true,
"self": 28.516229823018648
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.6479999948824116e-05,
"count": 1,
"self": 3.6479999948824116e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.4848079020072,
"count": 672138,
"is_parallel": true,
"self": 14.386455708035157,
"children": {
"process_trajectory": {
"total": 248.1547271309721,
"count": 672138,
"is_parallel": true,
"self": 247.63574559697207,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5189815340000337,
"count": 4,
"is_parallel": true,
"self": 0.5189815340000337
}
}
},
"_update_policy": {
"total": 184.94362506299996,
"count": 90,
"is_parallel": true,
"self": 58.13255416100105,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.8110709019989,
"count": 4587,
"is_parallel": true,
"self": 126.8110709019989
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09973042199999327,
"count": 1,
"self": 0.0010014439999395108,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09872897800005376,
"count": 1,
"self": 0.09872897800005376
}
}
}
}
}
}
}