ezrab's picture
First Push
c918a73 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.902777373790741,
"min": 0.902777373790741,
"max": 2.835435152053833,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8579.99609375,
"min": 8579.99609375,
"max": 28944.123046875,
"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": 12.439536094665527,
"min": 0.5278654098510742,
"max": 12.439536094665527,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2425.70947265625,
"min": 102.4058837890625,
"max": 2479.1435546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06146877399499086,
"min": 0.06043116850866913,
"max": 0.07431257622642899,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24587509597996343,
"min": 0.2417246740346765,
"max": 0.371562881132145,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20411697855474903,
"min": 0.16378362063665453,
"max": 0.27187204967234646,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8164679142189961,
"min": 0.6551344825466181,
"max": 1.3536074047579485,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.022727272727273,
"min": 4.681818181818182,
"max": 25.022727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1101.0,
"min": 206.0,
"max": 1352.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.022727272727273,
"min": 4.681818181818182,
"max": 25.022727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1101.0,
"min": 206.0,
"max": 1352.0,
"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": "1741120509",
"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=SnowballTarget2 --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": "1741120962"
},
"total": 452.3098513749999,
"count": 1,
"self": 0.4760865509999803,
"children": {
"run_training.setup": {
"total": 0.020242470000084722,
"count": 1,
"self": 0.020242470000084722
},
"TrainerController.start_learning": {
"total": 451.8135223539998,
"count": 1,
"self": 0.3582307819790458,
"children": {
"TrainerController._reset_env": {
"total": 1.9031524419999641,
"count": 1,
"self": 1.9031524419999641
},
"TrainerController.advance": {
"total": 448.9504144930206,
"count": 18192,
"self": 0.37845969800810053,
"children": {
"env_step": {
"total": 306.74346253901786,
"count": 18192,
"self": 230.69257967304316,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.84292613099547,
"count": 18192,
"self": 1.279624233983668,
"children": {
"TorchPolicy.evaluate": {
"total": 74.5633018970118,
"count": 18192,
"self": 74.5633018970118
}
}
},
"workers": {
"total": 0.20795673497923417,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.45180412199034,
"count": 18192,
"is_parallel": true,
"self": 246.7355616719815,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022199799998361414,
"count": 1,
"is_parallel": true,
"self": 0.0007270940000125847,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014928859998235566,
"count": 10,
"is_parallel": true,
"self": 0.0014928859998235566
}
}
},
"UnityEnvironment.step": {
"total": 0.03713981900000363,
"count": 1,
"is_parallel": true,
"self": 0.0005536630001188314,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036533299999064184,
"count": 1,
"is_parallel": true,
"self": 0.00036533299999064184
},
"communicator.exchange": {
"total": 0.03434045599988167,
"count": 1,
"is_parallel": true,
"self": 0.03434045599988167
},
"steps_from_proto": {
"total": 0.001880367000012484,
"count": 1,
"is_parallel": true,
"self": 0.0003563020006822626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015240649993302213,
"count": 10,
"is_parallel": true,
"self": 0.0015240649993302213
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.71624245000885,
"count": 18191,
"is_parallel": true,
"self": 9.57061088599471,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.299452625998811,
"count": 18191,
"is_parallel": true,
"self": 5.299452625998811
},
"communicator.exchange": {
"total": 156.00230253200766,
"count": 18191,
"is_parallel": true,
"self": 156.00230253200766
},
"steps_from_proto": {
"total": 31.843876406007666,
"count": 18191,
"is_parallel": true,
"self": 5.749270220983817,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.09460618502385,
"count": 181910,
"is_parallel": true,
"self": 26.09460618502385
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 141.82849225599466,
"count": 18192,
"self": 0.41393678399958844,
"children": {
"process_trajectory": {
"total": 30.356777120995503,
"count": 18192,
"self": 28.193488136995484,
"children": {
"RLTrainer._checkpoint": {
"total": 2.163288984000019,
"count": 4,
"self": 2.163288984000019
}
}
},
"_update_policy": {
"total": 111.05777835099957,
"count": 90,
"self": 38.621671692993004,
"children": {
"TorchPPOOptimizer.update": {
"total": 72.43610665800657,
"count": 4587,
"self": 72.43610665800657
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2790001164830755e-06,
"count": 1,
"self": 1.2790001164830755e-06
},
"TrainerController._save_models": {
"total": 0.601723358000072,
"count": 1,
"self": 0.019209138000178427,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5825142199998936,
"count": 1,
"self": 0.5825142199998936
}
}
}
}
}
}
}