ppo-Huggy2 / run_logs /timers.json
anthonyx's picture
Huggy
a5246d6
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3737354278564453,
"min": 1.3737354278564453,
"max": 1.4190611839294434,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 67387.21875,
"min": 67222.984375,
"max": 78129.25,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.97092084006462,
"min": 74.58904109589041,
"max": 384.8473282442748,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48883.0,
"min": 48850.0,
"max": 50415.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999895.0,
"min": 49947.0,
"max": 1999895.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999895.0,
"min": 49947.0,
"max": 1999895.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3876590728759766,
"min": 0.05429534241557121,
"max": 2.4671123027801514,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1477.9609375,
"min": 7.058394432067871,
"max": 1578.869140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.700561510149227,
"min": 1.8164270959794522,
"max": 3.9352521559125497,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2290.6475747823715,
"min": 236.13552247732878,
"max": 2523.290436029434,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.700561510149227,
"min": 1.8164270959794522,
"max": 3.9352521559125497,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2290.6475747823715,
"min": 236.13552247732878,
"max": 2523.290436029434,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017730468319496137,
"min": 0.013496995696914382,
"max": 0.019073133331322528,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05319140495848841,
"min": 0.026993991393828763,
"max": 0.05721939999396758,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05081416095296542,
"min": 0.019599376060068605,
"max": 0.05081416095296542,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15244248285889625,
"min": 0.03919875212013721,
"max": 0.15244248285889625,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.393548868850009e-06,
"min": 3.393548868850009e-06,
"max": 0.0002953533765488749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0180646606550027e-05,
"min": 1.0180646606550027e-05,
"max": 0.0008442088685970498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113115000000002,
"min": 0.10113115000000002,
"max": 0.19845112500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30339345000000006,
"min": 0.20748544999999993,
"max": 0.5814029499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.644438500000016e-05,
"min": 6.644438500000016e-05,
"max": 0.004922711137499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001993331550000005,
"min": 0.0001993331550000005,
"max": 0.014072007205000002,
"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": "1679386638",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679389134"
},
"total": 2495.9354726089996,
"count": 1,
"self": 0.42609999099931883,
"children": {
"run_training.setup": {
"total": 0.10723239599997214,
"count": 1,
"self": 0.10723239599997214
},
"TrainerController.start_learning": {
"total": 2495.402140222,
"count": 1,
"self": 4.385872131018459,
"children": {
"TrainerController._reset_env": {
"total": 8.569250894999982,
"count": 1,
"self": 8.569250894999982
},
"TrainerController.advance": {
"total": 2481.307666987981,
"count": 232464,
"self": 4.7283330239570205,
"children": {
"env_step": {
"total": 1838.5059599740846,
"count": 232464,
"self": 1510.3624134751076,
"children": {
"SubprocessEnvManager._take_step": {
"total": 325.34822409604755,
"count": 232464,
"self": 17.423733689043274,
"children": {
"TorchPolicy.evaluate": {
"total": 307.92449040700427,
"count": 222894,
"self": 307.92449040700427
}
}
},
"workers": {
"total": 2.7953224029294006,
"count": 232464,
"self": 0.0,
"children": {
"worker_root": {
"total": 2485.774630352848,
"count": 232464,
"is_parallel": true,
"self": 1263.244197982894,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001432529999988219,
"count": 1,
"is_parallel": true,
"self": 0.00038000000000693035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010525299999812887,
"count": 2,
"is_parallel": true,
"self": 0.0010525299999812887
}
}
},
"UnityEnvironment.step": {
"total": 0.031518215999994936,
"count": 1,
"is_parallel": true,
"self": 0.0004041760000177419,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044920000004822214,
"count": 1,
"is_parallel": true,
"self": 0.00044920000004822214
},
"communicator.exchange": {
"total": 0.029899330999967333,
"count": 1,
"is_parallel": true,
"self": 0.029899330999967333
},
"steps_from_proto": {
"total": 0.0007655089999616393,
"count": 1,
"is_parallel": true,
"self": 0.0002732480000418036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004922609999198357,
"count": 2,
"is_parallel": true,
"self": 0.0004922609999198357
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1222.5304323699538,
"count": 232463,
"is_parallel": true,
"self": 38.49578113298435,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 75.77910715099421,
"count": 232463,
"is_parallel": true,
"self": 75.77910715099421
},
"communicator.exchange": {
"total": 1019.4711273040195,
"count": 232463,
"is_parallel": true,
"self": 1019.4711273040195
},
"steps_from_proto": {
"total": 88.78441678195577,
"count": 232463,
"is_parallel": true,
"self": 33.66876727289991,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.11564950905586,
"count": 464926,
"is_parallel": true,
"self": 55.11564950905586
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 638.0733739899397,
"count": 232464,
"self": 6.689532198881807,
"children": {
"process_trajectory": {
"total": 159.28371722905814,
"count": 232464,
"self": 151.88153419105817,
"children": {
"RLTrainer._checkpoint": {
"total": 7.402183037999976,
"count": 10,
"self": 7.402183037999976
}
}
},
"_update_policy": {
"total": 472.10012456199973,
"count": 97,
"self": 317.5197455159927,
"children": {
"TorchPPOOptimizer.update": {
"total": 154.580379046007,
"count": 2910,
"self": 154.580379046007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.620002856536303e-07,
"count": 1,
"self": 9.620002856536303e-07
},
"TrainerController._save_models": {
"total": 1.1393492460001653,
"count": 1,
"self": 0.05318348600030731,
"children": {
"RLTrainer._checkpoint": {
"total": 1.086165759999858,
"count": 1,
"self": 1.086165759999858
}
}
}
}
}
}
}