ppo-Huggy / run_logs /timers.json
PedroPlusPlus's picture
Huggy
341f312 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4101495742797852,
"min": 1.4101495742797852,
"max": 1.4299265146255493,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70800.7890625,
"min": 68227.65625,
"max": 77815.0390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 110.44320712694878,
"min": 90.38939670932358,
"max": 408.6910569105691,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49589.0,
"min": 48931.0,
"max": 50269.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49867.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49867.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.428973913192749,
"min": 0.10059806704521179,
"max": 2.4592974185943604,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1090.6092529296875,
"min": 12.272964477539062,
"max": 1311.126220703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.838947568014098,
"min": 1.8529711647844704,
"max": 3.945932425519146,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1723.68745803833,
"min": 226.0624821037054,
"max": 2032.6810573935509,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.838947568014098,
"min": 1.8529711647844704,
"max": 3.945932425519146,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1723.68745803833,
"min": 226.0624821037054,
"max": 2032.6810573935509,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01745360365409094,
"min": 0.0141959595658894,
"max": 0.020306644701364954,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03490720730818188,
"min": 0.0283919191317788,
"max": 0.05895795497150781,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.047724770009517664,
"min": 0.021939619568487008,
"max": 0.05485060935219129,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09544954001903533,
"min": 0.043879239136974016,
"max": 0.16455182805657387,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.485248504950009e-06,
"min": 4.485248504950009e-06,
"max": 0.00029535645154785,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.970497009900018e-06,
"min": 8.970497009900018e-06,
"max": 0.0008441070186309999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10149505000000002,
"min": 0.10149505000000002,
"max": 0.19845215,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20299010000000003,
"min": 0.20299010000000003,
"max": 0.5813689999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.460299500000014e-05,
"min": 8.460299500000014e-05,
"max": 0.004922762284999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001692059900000003,
"min": 0.0001692059900000003,
"max": 0.014070313099999999,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1726303035",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --force --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726305925"
},
"total": 2890.5575990260004,
"count": 1,
"self": 0.4393069950001518,
"children": {
"run_training.setup": {
"total": 0.057343575999993845,
"count": 1,
"self": 0.057343575999993845
},
"TrainerController.start_learning": {
"total": 2890.0609484550005,
"count": 1,
"self": 5.284108494914108,
"children": {
"TrainerController._reset_env": {
"total": 2.096197521000022,
"count": 1,
"self": 2.096197521000022
},
"TrainerController.advance": {
"total": 2882.5620195610854,
"count": 231669,
"self": 5.532749395945757,
"children": {
"env_step": {
"total": 2328.9420655131084,
"count": 231669,
"self": 1834.322656763008,
"children": {
"SubprocessEnvManager._take_step": {
"total": 491.03314868908956,
"count": 231669,
"self": 18.773150770111442,
"children": {
"TorchPolicy.evaluate": {
"total": 472.2599979189781,
"count": 223048,
"self": 472.2599979189781
}
}
},
"workers": {
"total": 3.5862600610109894,
"count": 231669,
"self": 0.0,
"children": {
"worker_root": {
"total": 2881.8484054420946,
"count": 231669,
"is_parallel": true,
"self": 1405.4691018020812,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009064769999440614,
"count": 1,
"is_parallel": true,
"self": 0.0002907219998178334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000615755000126228,
"count": 2,
"is_parallel": true,
"self": 0.000615755000126228
}
}
},
"UnityEnvironment.step": {
"total": 0.056933264999997846,
"count": 1,
"is_parallel": true,
"self": 0.0004737399999612535,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020655899993471394,
"count": 1,
"is_parallel": true,
"self": 0.00020655899993471394
},
"communicator.exchange": {
"total": 0.05533665000007204,
"count": 1,
"is_parallel": true,
"self": 0.05533665000007204
},
"steps_from_proto": {
"total": 0.0009163160000298376,
"count": 1,
"is_parallel": true,
"self": 0.0002259860000322078,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006903299999976298,
"count": 2,
"is_parallel": true,
"self": 0.0006903299999976298
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1476.3793036400134,
"count": 231668,
"is_parallel": true,
"self": 42.795902395216444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 99.10413458697622,
"count": 231668,
"is_parallel": true,
"self": 99.10413458697622
},
"communicator.exchange": {
"total": 1230.1889245537843,
"count": 231668,
"is_parallel": true,
"self": 1230.1889245537843
},
"steps_from_proto": {
"total": 104.29034210403643,
"count": 231668,
"is_parallel": true,
"self": 40.021844037120445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.26849806691598,
"count": 463336,
"is_parallel": true,
"self": 64.26849806691598
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 548.0872046520312,
"count": 231669,
"self": 7.719655113098497,
"children": {
"process_trajectory": {
"total": 188.8950610889301,
"count": 231669,
"self": 187.30397970293006,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5910813860000417,
"count": 10,
"self": 1.5910813860000417
}
}
},
"_update_policy": {
"total": 351.47248845000263,
"count": 96,
"self": 283.04204543401465,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.43044301598798,
"count": 2880,
"self": 68.43044301598798
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0440007827128284e-06,
"count": 1,
"self": 1.0440007827128284e-06
},
"TrainerController._save_models": {
"total": 0.1186218339998959,
"count": 1,
"self": 0.0018670829995244276,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11675475100037147,
"count": 1,
"self": 0.11675475100037147
}
}
}
}
}
}
}