saxelsso's picture
First Push
d24191a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9683467149734497,
"min": 0.9683467149734497,
"max": 2.872779607772827,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9267.078125,
"min": 9267.078125,
"max": 29420.13671875,
"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": 12.876216888427734,
"min": 0.23242877423763275,
"max": 12.876216888427734,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.8623046875,
"min": 45.091182708740234,
"max": 2618.16259765625,
"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": 0.06663086534628711,
"min": 0.06373689487415558,
"max": 0.07624845468372395,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26652346138514843,
"min": 0.25494757949662233,
"max": 0.3746431804348842,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19587464857043008,
"min": 0.0946855520311396,
"max": 0.32509992654417075,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7834985942817203,
"min": 0.3787422081245584,
"max": 1.6254996327208537,
"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": 25.15909090909091,
"min": 2.6363636363636362,
"max": 25.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 116.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 2.6363636363636362,
"max": 25.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 116.0,
"max": 1377.0,
"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": "1736437318",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736437959"
},
"total": 641.4138268690001,
"count": 1,
"self": 0.5286531640001613,
"children": {
"run_training.setup": {
"total": 0.07444102300001987,
"count": 1,
"self": 0.07444102300001987
},
"TrainerController.start_learning": {
"total": 640.810732682,
"count": 1,
"self": 0.9342563530010466,
"children": {
"TrainerController._reset_env": {
"total": 7.372795256000018,
"count": 1,
"self": 7.372795256000018
},
"TrainerController.advance": {
"total": 632.4151949849988,
"count": 18203,
"self": 0.45687584799418346,
"children": {
"env_step": {
"total": 631.9583191370047,
"count": 18203,
"self": 486.9164910800235,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.5814199859916,
"count": 18203,
"self": 2.6646738559994674,
"children": {
"TorchPolicy.evaluate": {
"total": 141.91674612999213,
"count": 18203,
"self": 141.91674612999213
}
}
},
"workers": {
"total": 0.4604080709895584,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 638.7057888129985,
"count": 18203,
"is_parallel": true,
"self": 304.95955236800995,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027081060000000434,
"count": 1,
"is_parallel": true,
"self": 0.0007763419999378129,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019317640000622305,
"count": 10,
"is_parallel": true,
"self": 0.0019317640000622305
}
}
},
"UnityEnvironment.step": {
"total": 0.04674543999999514,
"count": 1,
"is_parallel": true,
"self": 0.001009000999943055,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005432410000025811,
"count": 1,
"is_parallel": true,
"self": 0.0005432410000025811
},
"communicator.exchange": {
"total": 0.04256321299999399,
"count": 1,
"is_parallel": true,
"self": 0.04256321299999399
},
"steps_from_proto": {
"total": 0.0026299850000555125,
"count": 1,
"is_parallel": true,
"self": 0.0005234629999790741,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021065220000764384,
"count": 10,
"is_parallel": true,
"self": 0.0021065220000764384
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 333.7462364449886,
"count": 18202,
"is_parallel": true,
"self": 15.59106928300099,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.979942958997299,
"count": 18202,
"is_parallel": true,
"self": 7.979942958997299
},
"communicator.exchange": {
"total": 263.5708117709945,
"count": 18202,
"is_parallel": true,
"self": 263.5708117709945
},
"steps_from_proto": {
"total": 46.6044124319958,
"count": 18202,
"is_parallel": true,
"self": 9.390994478008679,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.21341795398712,
"count": 182020,
"is_parallel": true,
"self": 37.21341795398712
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021327100000689825,
"count": 1,
"self": 0.00021327100000689825,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 625.1303069839298,
"count": 806019,
"is_parallel": true,
"self": 18.002380432881637,
"children": {
"process_trajectory": {
"total": 337.22763786404795,
"count": 806019,
"is_parallel": true,
"self": 336.0222897880479,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2053480760000639,
"count": 4,
"is_parallel": true,
"self": 1.2053480760000639
}
}
},
"_update_policy": {
"total": 269.9002886870002,
"count": 90,
"is_parallel": true,
"self": 76.32622847800354,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.57406020899668,
"count": 4587,
"is_parallel": true,
"self": 193.57406020899668
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08827281700007461,
"count": 1,
"self": 0.0012389620001158619,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08703385499995875,
"count": 1,
"self": 0.08703385499995875
}
}
}
}
}
}
}