ppo-Huggy / run_logs /timers.json
akhalinem's picture
Huggy
06be649 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4026141166687012,
"min": 1.4025956392288208,
"max": 1.4256380796432495,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69721.140625,
"min": 68671.390625,
"max": 77061.1328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.20524691358025,
"min": 74.30271084337349,
"max": 392.6640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49381.0,
"min": 49004.0,
"max": 50261.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49956.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49956.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.461968421936035,
"min": 0.0999968871474266,
"max": 2.486962080001831,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1595.35546875,
"min": 12.699604988098145,
"max": 1633.475830078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8708141956616333,
"min": 1.7059477585272527,
"max": 3.980414941306707,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2508.2875987887383,
"min": 216.65536533296108,
"max": 2585.8045521378517,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8708141956616333,
"min": 1.7059477585272527,
"max": 3.980414941306707,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2508.2875987887383,
"min": 216.65536533296108,
"max": 2585.8045521378517,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01415927364467077,
"min": 0.013411353012331045,
"max": 0.019200525572099045,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04247782093401231,
"min": 0.028094341711645633,
"max": 0.05600758354800443,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05694516205953227,
"min": 0.023514736350625752,
"max": 0.06955742904295524,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1708354861785968,
"min": 0.047029472701251504,
"max": 0.1810352187603712,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7705487431833247e-06,
"min": 3.7705487431833247e-06,
"max": 0.00029532922655692496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1311646229549974e-05,
"min": 1.1311646229549974e-05,
"max": 0.0008441911686029502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125681666666664,
"min": 0.10125681666666664,
"max": 0.19844307500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037704499999999,
"min": 0.20764780000000002,
"max": 0.58139705,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.271515166666654e-05,
"min": 7.271515166666654e-05,
"max": 0.0049223094425,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021814545499999964,
"min": 0.00021814545499999964,
"max": 0.014071712795,
"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": "1709404564",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709407083"
},
"total": 2519.028019699,
"count": 1,
"self": 0.49258273999976154,
"children": {
"run_training.setup": {
"total": 0.06840644999999768,
"count": 1,
"self": 0.06840644999999768
},
"TrainerController.start_learning": {
"total": 2518.4670305090003,
"count": 1,
"self": 4.783274994023486,
"children": {
"TrainerController._reset_env": {
"total": 3.1689228559999947,
"count": 1,
"self": 3.1689228559999947
},
"TrainerController.advance": {
"total": 2510.379440527977,
"count": 232816,
"self": 5.131177188945458,
"children": {
"env_step": {
"total": 2023.114637565023,
"count": 232816,
"self": 1679.163881838105,
"children": {
"SubprocessEnvManager._take_step": {
"total": 340.857859049881,
"count": 232816,
"self": 18.821899990960333,
"children": {
"TorchPolicy.evaluate": {
"total": 322.03595905892064,
"count": 222940,
"self": 322.03595905892064
}
}
},
"workers": {
"total": 3.0928966770370607,
"count": 232816,
"self": 0.0,
"children": {
"worker_root": {
"total": 2510.895431248109,
"count": 232816,
"is_parallel": true,
"self": 1143.2241190820894,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009206099999801154,
"count": 1,
"is_parallel": true,
"self": 0.00022624300004281395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006943669999373014,
"count": 2,
"is_parallel": true,
"self": 0.0006943669999373014
}
}
},
"UnityEnvironment.step": {
"total": 0.03147975199999564,
"count": 1,
"is_parallel": true,
"self": 0.00030265300006249163,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020277199996598938,
"count": 1,
"is_parallel": true,
"self": 0.00020277199996598938
},
"communicator.exchange": {
"total": 0.03021883799999614,
"count": 1,
"is_parallel": true,
"self": 0.03021883799999614
},
"steps_from_proto": {
"total": 0.0007554889999710213,
"count": 1,
"is_parallel": true,
"self": 0.00023621200000434328,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000519276999966678,
"count": 2,
"is_parallel": true,
"self": 0.000519276999966678
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1367.6713121660198,
"count": 232815,
"is_parallel": true,
"self": 42.32185491282985,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.6763642780437,
"count": 232815,
"is_parallel": true,
"self": 91.6763642780437
},
"communicator.exchange": {
"total": 1136.4783859301538,
"count": 232815,
"is_parallel": true,
"self": 1136.4783859301538
},
"steps_from_proto": {
"total": 97.19470704499236,
"count": 232815,
"is_parallel": true,
"self": 36.51595754286723,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.67874950212513,
"count": 465630,
"is_parallel": true,
"self": 60.67874950212513
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 482.13362577400835,
"count": 232816,
"self": 6.98837535908774,
"children": {
"process_trajectory": {
"total": 166.33352861291883,
"count": 232816,
"self": 165.03336649891844,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3001621140003863,
"count": 10,
"self": 1.3001621140003863
}
}
},
"_update_policy": {
"total": 308.8117218020018,
"count": 97,
"self": 246.832408719996,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.979313082005774,
"count": 2910,
"self": 61.979313082005774
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.139000232797116e-06,
"count": 1,
"self": 1.139000232797116e-06
},
"TrainerController._save_models": {
"total": 0.13539099199988414,
"count": 1,
"self": 0.002135641999757354,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13325535000012678,
"count": 1,
"self": 0.13325535000012678
}
}
}
}
}
}
}