Ankit Kumar
First Push
3be3d52
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8103706240653992,
"min": 0.807844340801239,
"max": 2.8515784740448,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8325.748046875,
"min": 7735.56884765625,
"max": 29203.015625,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.46130084991455,
"min": 0.40719178318977356,
"max": 13.49724006652832,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2746.10546875,
"min": 78.99520874023438,
"max": 2749.92041015625,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.050455696602148235,
"min": 0.03958451389280526,
"max": 0.05132645800586033,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2522784830107412,
"min": 0.15833805557122105,
"max": 0.25396518236266274,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19039288042113184,
"min": 0.11913659021956846,
"max": 0.2871275396086276,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9519644021056592,
"min": 0.47654636087827384,
"max": 1.4356376980431378,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.0507649039999975e-06,
"min": 7.0507649039999975e-06,
"max": 0.000392784001804,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.525382451999999e-05,
"min": 3.525382451999999e-05,
"max": 0.0018979200255200002,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10176266666666667,
"min": 0.10176266666666667,
"max": 0.198196,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5088133333333333,
"min": 0.42025066666666666,
"max": 0.9744800000000001,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.795706666666662e-05,
"min": 9.795706666666662e-05,
"max": 0.0049099804000000006,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004897853333333331,
"min": 0.0004897853333333331,
"max": 0.023726551999999998,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.036363636363635,
"min": 3.340909090909091,
"max": 26.75,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1432.0,
"min": 147.0,
"max": 1444.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.036363636363635,
"min": 3.340909090909091,
"max": 26.75,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1432.0,
"min": 147.0,
"max": 1444.0,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697616259",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697616965"
},
"total": 706.6390929570002,
"count": 1,
"self": 0.4364265060003163,
"children": {
"run_training.setup": {
"total": 0.06732300900011978,
"count": 1,
"self": 0.06732300900011978
},
"TrainerController.start_learning": {
"total": 706.1353434419998,
"count": 1,
"self": 0.84929457697217,
"children": {
"TrainerController._reset_env": {
"total": 7.04299500299976,
"count": 1,
"self": 7.04299500299976
},
"TrainerController.advance": {
"total": 698.1503826300273,
"count": 27333,
"self": 0.40815560900819037,
"children": {
"env_step": {
"total": 697.7422270210191,
"count": 27333,
"self": 456.0188004540091,
"children": {
"SubprocessEnvManager._take_step": {
"total": 241.2230645270506,
"count": 27333,
"self": 2.159738381018542,
"children": {
"TorchPolicy.evaluate": {
"total": 239.06332614603207,
"count": 27333,
"self": 239.06332614603207
}
}
},
"workers": {
"total": 0.5003620399593274,
"count": 27333,
"self": 0.0,
"children": {
"worker_root": {
"total": 704.255705640041,
"count": 27333,
"is_parallel": true,
"self": 341.37024536006993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006655250000221713,
"count": 1,
"is_parallel": true,
"self": 0.004301365000173973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023538850000477396,
"count": 10,
"is_parallel": true,
"self": 0.0023538850000477396
}
}
},
"UnityEnvironment.step": {
"total": 0.051917810999839276,
"count": 1,
"is_parallel": true,
"self": 0.0007285470001079375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004718549998870003,
"count": 1,
"is_parallel": true,
"self": 0.0004718549998870003
},
"communicator.exchange": {
"total": 0.048757182999906945,
"count": 1,
"is_parallel": true,
"self": 0.048757182999906945
},
"steps_from_proto": {
"total": 0.0019602259999373928,
"count": 1,
"is_parallel": true,
"self": 0.00046687600024597486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001493349999691418,
"count": 10,
"is_parallel": true,
"self": 0.001493349999691418
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 362.8854602799711,
"count": 27332,
"is_parallel": true,
"self": 16.130657274954956,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.320938625029157,
"count": 27332,
"is_parallel": true,
"self": 8.320938625029157
},
"communicator.exchange": {
"total": 285.7860269790258,
"count": 27332,
"is_parallel": true,
"self": 285.7860269790258
},
"steps_from_proto": {
"total": 52.64783740096118,
"count": 27332,
"is_parallel": true,
"self": 9.919021880005857,
"children": {
"_process_rank_one_or_two_observation": {
"total": 42.72881552095532,
"count": 273320,
"is_parallel": true,
"self": 42.72881552095532
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00047883100023682346,
"count": 1,
"self": 0.00047883100023682346,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 692.4570996939433,
"count": 715583,
"is_parallel": true,
"self": 15.38329598588507,
"children": {
"process_trajectory": {
"total": 393.0956603900563,
"count": 715583,
"is_parallel": true,
"self": 391.8519399300567,
"children": {
"RLTrainer._checkpoint": {
"total": 1.243720459999622,
"count": 6,
"is_parallel": true,
"self": 1.243720459999622
}
}
},
"_update_policy": {
"total": 283.9781433180019,
"count": 136,
"is_parallel": true,
"self": 118.71959624499868,
"children": {
"TorchPPOOptimizer.update": {
"total": 165.25854707300323,
"count": 4352,
"is_parallel": true,
"self": 165.25854707300323
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09219240100037496,
"count": 1,
"self": 0.0009243160002370132,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09126808500013794,
"count": 1,
"self": 0.09126808500013794
}
}
}
}
}
}
}