ashani's picture
First Push
c197287 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6633455157279968,
"min": 0.6507212519645691,
"max": 2.8374948501586914,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6304.435546875,
"min": 6304.435546875,
"max": 28965.1484375,
"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": 13.073689460754395,
"min": 0.40250498056411743,
"max": 13.073689460754395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2549.369384765625,
"min": 78.08596801757812,
"max": 2630.43017578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07322675079536994,
"min": 0.06265492161202893,
"max": 0.07710177242052832,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2929070031814798,
"min": 0.2531409292863043,
"max": 0.37075016676681116,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18968608632099393,
"min": 0.11642043488317025,
"max": 0.27866208794362407,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7587443452839757,
"min": 0.465681739532681,
"max": 1.3361737844990749,
"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": 26.0,
"min": 3.409090909090909,
"max": 26.072727272727274,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1144.0,
"min": 150.0,
"max": 1434.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.0,
"min": 3.409090909090909,
"max": 26.072727272727274,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1144.0,
"min": 150.0,
"max": 1434.0,
"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": "1748250099",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748250537"
},
"total": 437.78520168500006,
"count": 1,
"self": 0.4379386880000311,
"children": {
"run_training.setup": {
"total": 0.022889133999967726,
"count": 1,
"self": 0.022889133999967726
},
"TrainerController.start_learning": {
"total": 437.32437386300006,
"count": 1,
"self": 0.388163965007152,
"children": {
"TrainerController._reset_env": {
"total": 3.1427827059999913,
"count": 1,
"self": 3.1427827059999913
},
"TrainerController.advance": {
"total": 433.71421101799285,
"count": 18192,
"self": 0.40085193400716435,
"children": {
"env_step": {
"total": 310.34734026099176,
"count": 18192,
"self": 237.9033961310032,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.21964554599492,
"count": 18192,
"self": 1.3201132939994977,
"children": {
"TorchPolicy.evaluate": {
"total": 70.89953225199542,
"count": 18192,
"self": 70.89953225199542
}
}
},
"workers": {
"total": 0.22429858399362956,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.8804343559989,
"count": 18192,
"is_parallel": true,
"self": 227.44002641499395,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005201473999989048,
"count": 1,
"is_parallel": true,
"self": 0.003694509999888851,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015069640001001972,
"count": 10,
"is_parallel": true,
"self": 0.0015069640001001972
}
}
},
"UnityEnvironment.step": {
"total": 0.037346167999999125,
"count": 1,
"is_parallel": true,
"self": 0.000581679000049462,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042554700002028767,
"count": 1,
"is_parallel": true,
"self": 0.00042554700002028767
},
"communicator.exchange": {
"total": 0.03453737299997783,
"count": 1,
"is_parallel": true,
"self": 0.03453737299997783
},
"steps_from_proto": {
"total": 0.0018015689999515416,
"count": 1,
"is_parallel": true,
"self": 0.00033908600011045564,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001462482999841086,
"count": 10,
"is_parallel": true,
"self": 0.001462482999841086
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.44040794100493,
"count": 18191,
"is_parallel": true,
"self": 9.993178141004876,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.57224824000383,
"count": 18191,
"is_parallel": true,
"self": 5.57224824000383
},
"communicator.exchange": {
"total": 160.35184897099663,
"count": 18191,
"is_parallel": true,
"self": 160.35184897099663
},
"steps_from_proto": {
"total": 32.5231325889996,
"count": 18191,
"is_parallel": true,
"self": 5.993853799021508,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.529278789978093,
"count": 181910,
"is_parallel": true,
"self": 26.529278789978093
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.96601882299393,
"count": 18192,
"self": 0.47662654398715176,
"children": {
"process_trajectory": {
"total": 28.026131855006668,
"count": 18192,
"self": 27.60922351700657,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4169083380000984,
"count": 4,
"self": 0.4169083380000984
}
}
},
"_update_policy": {
"total": 94.46326042400011,
"count": 90,
"self": 38.80068080400258,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.66257961999753,
"count": 4587,
"self": 55.66257961999753
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.290000662076636e-07,
"count": 1,
"self": 9.290000662076636e-07
},
"TrainerController._save_models": {
"total": 0.07921524500000032,
"count": 1,
"self": 0.0007626079999454305,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07845263700005489,
"count": 1,
"self": 0.07845263700005489
}
}
}
}
}
}
}