ProrabVasili's picture
First Push
4222363 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.441195011138916,
"min": 1.441195011138916,
"max": 2.88092303276062,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13887.35546875,
"min": 13887.35546875,
"max": 29598.603515625,
"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": 6.423199653625488,
"min": 0.292542040348053,
"max": 6.423199653625488,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1252.52392578125,
"min": 56.75315475463867,
"max": 1284.02294921875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06462002179272103,
"min": 0.06348656075430222,
"max": 0.07799287688035025,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2584800871708841,
"min": 0.25394624301720886,
"max": 0.38996438440175124,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1741166824803633,
"min": 0.08146316328944236,
"max": 0.23636911970143226,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6964667299214532,
"min": 0.32585265315776946,
"max": 1.0584121711698233,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.735097306000005e-06,
"min": 6.735097306000005e-06,
"max": 0.000243235002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.694038922400002e-05,
"min": 2.694038922400002e-05,
"max": 0.00115430003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.3999999999999999,
"min": 0.3999999999999999,
"max": 0.4999999999999999,
"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": 25.545454545454547,
"min": 3.0,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 132.0,
"max": 1372.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.0,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 132.0,
"max": 1372.0,
"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": "1720957838",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720958341"
},
"total": 503.7295814979998,
"count": 1,
"self": 0.4403192270001455,
"children": {
"run_training.setup": {
"total": 0.05633661399997436,
"count": 1,
"self": 0.05633661399997436
},
"TrainerController.start_learning": {
"total": 503.23292565699967,
"count": 1,
"self": 0.6099341250137513,
"children": {
"TrainerController._reset_env": {
"total": 2.8611745880002672,
"count": 1,
"self": 2.8611745880002672
},
"TrainerController.advance": {
"total": 499.6145293579857,
"count": 18209,
"self": 0.2933157549741736,
"children": {
"env_step": {
"total": 499.32121360301153,
"count": 18209,
"self": 316.1885072750051,
"children": {
"SubprocessEnvManager._take_step": {
"total": 182.8311652989978,
"count": 18209,
"self": 1.7861449000197354,
"children": {
"TorchPolicy.evaluate": {
"total": 181.04502039897807,
"count": 18209,
"self": 181.04502039897807
}
}
},
"workers": {
"total": 0.3015410290086038,
"count": 18209,
"self": 0.0,
"children": {
"worker_root": {
"total": 501.7898898960052,
"count": 18209,
"is_parallel": true,
"self": 266.2777514700283,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0055738639998708095,
"count": 1,
"is_parallel": true,
"self": 0.003982436000569578,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015914279993012315,
"count": 10,
"is_parallel": true,
"self": 0.0015914279993012315
}
}
},
"UnityEnvironment.step": {
"total": 0.040618771000026754,
"count": 1,
"is_parallel": true,
"self": 0.0007220719999168068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042904400015686406,
"count": 1,
"is_parallel": true,
"self": 0.00042904400015686406
},
"communicator.exchange": {
"total": 0.03737208599977748,
"count": 1,
"is_parallel": true,
"self": 0.03737208599977748
},
"steps_from_proto": {
"total": 0.002095569000175601,
"count": 1,
"is_parallel": true,
"self": 0.0003945700000258512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00170099900014975,
"count": 10,
"is_parallel": true,
"self": 0.00170099900014975
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.5121384259769,
"count": 18208,
"is_parallel": true,
"self": 10.660478185951433,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.7459591350161645,
"count": 18208,
"is_parallel": true,
"self": 5.7459591350161645
},
"communicator.exchange": {
"total": 183.1931483439671,
"count": 18208,
"is_parallel": true,
"self": 183.1931483439671
},
"steps_from_proto": {
"total": 35.91255276104221,
"count": 18208,
"is_parallel": true,
"self": 6.795533389102275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.117019371939932,
"count": 182080,
"is_parallel": true,
"self": 29.117019371939932
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014011999974172795,
"count": 1,
"self": 0.00014011999974172795,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 494.49532546078217,
"count": 611382,
"is_parallel": true,
"self": 13.526216300738724,
"children": {
"process_trajectory": {
"total": 288.2481225370457,
"count": 611382,
"is_parallel": true,
"self": 286.46236309504593,
"children": {
"RLTrainer._checkpoint": {
"total": 1.785759441999744,
"count": 4,
"is_parallel": true,
"self": 1.785759441999744
}
}
},
"_update_policy": {
"total": 192.72098662299777,
"count": 90,
"is_parallel": true,
"self": 59.535113113999614,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.18587350899816,
"count": 4584,
"is_parallel": true,
"self": 133.18587350899816
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1471474660002059,
"count": 1,
"self": 0.0009597960006431094,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14618766999956279,
"count": 1,
"self": 0.14618766999956279
}
}
}
}
}
}
}