ppo-Huggy / run_logs /timers.json
TheHelltaker's picture
Huggy
9e9a2f1 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4089967012405396,
"min": 1.4089967012405396,
"max": 1.4278881549835205,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69858.0546875,
"min": 69467.953125,
"max": 77015.96875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.75264270613108,
"min": 81.97,
"max": 414.8032786885246,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49548.0,
"min": 48905.0,
"max": 50606.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999952.0,
"min": 49978.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999952.0,
"min": 49978.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.40217661857605,
"min": 0.23749737441539764,
"max": 2.4512991905212402,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1136.2294921875,
"min": 28.7371826171875,
"max": 1443.306640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6427378640618433,
"min": 1.805066805979437,
"max": 3.96520248844002,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1723.015009701252,
"min": 218.4130835235119,
"max": 2375.0889550447464,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6427378640618433,
"min": 1.805066805979437,
"max": 3.96520248844002,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1723.015009701252,
"min": 218.4130835235119,
"max": 2375.0889550447464,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016991396101204575,
"min": 0.012708509897007995,
"max": 0.01971567994203522,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05097418830361372,
"min": 0.02541701979401599,
"max": 0.05914703982610566,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055486995230118435,
"min": 0.02023443756625056,
"max": 0.06012082130958636,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1664609856903553,
"min": 0.04046887513250112,
"max": 0.17886993587017058,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.330098890000011e-06,
"min": 3.330098890000011e-06,
"max": 0.0002953358265547249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.990296670000033e-06,
"min": 9.990296670000033e-06,
"max": 0.0008437977187340998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110999999999999,
"min": 0.10110999999999999,
"max": 0.19844527499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30333,
"min": 0.20738375,
"max": 0.5812659000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.538900000000018e-05,
"min": 6.538900000000018e-05,
"max": 0.0049224192225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019616700000000054,
"min": 0.00019616700000000054,
"max": 0.014065168409999999,
"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": "1752297337",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752299734"
},
"total": 2396.984319349,
"count": 1,
"self": 0.44565952699986155,
"children": {
"run_training.setup": {
"total": 0.03222625700004755,
"count": 1,
"self": 0.03222625700004755
},
"TrainerController.start_learning": {
"total": 2396.506433565,
"count": 1,
"self": 4.052068073060582,
"children": {
"TrainerController._reset_env": {
"total": 3.708710741999994,
"count": 1,
"self": 3.708710741999994
},
"TrainerController.advance": {
"total": 2388.6391079689397,
"count": 231991,
"self": 4.396128866921572,
"children": {
"env_step": {
"total": 1902.7162550180556,
"count": 231991,
"self": 1500.7686724590526,
"children": {
"SubprocessEnvManager._take_step": {
"total": 399.3822650949402,
"count": 231991,
"self": 15.34908244398082,
"children": {
"TorchPolicy.evaluate": {
"total": 384.03318265095936,
"count": 222994,
"self": 384.03318265095936
}
}
},
"workers": {
"total": 2.565317464062673,
"count": 231991,
"self": 0.0,
"children": {
"worker_root": {
"total": 2389.160205642995,
"count": 231991,
"is_parallel": true,
"self": 1164.69292969301,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010962989999825368,
"count": 1,
"is_parallel": true,
"self": 0.0002914329999157417,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008048660000667951,
"count": 2,
"is_parallel": true,
"self": 0.0008048660000667951
}
}
},
"UnityEnvironment.step": {
"total": 0.039844898999945144,
"count": 1,
"is_parallel": true,
"self": 0.0003062469999122186,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018930099997760408,
"count": 1,
"is_parallel": true,
"self": 0.00018930099997760408
},
"communicator.exchange": {
"total": 0.03863113500005966,
"count": 1,
"is_parallel": true,
"self": 0.03863113500005966
},
"steps_from_proto": {
"total": 0.0007182159999956639,
"count": 1,
"is_parallel": true,
"self": 0.00018608999994285114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005321260000528127,
"count": 2,
"is_parallel": true,
"self": 0.0005321260000528127
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1224.4672759499852,
"count": 231990,
"is_parallel": true,
"self": 36.517817772894205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.95513598707726,
"count": 231990,
"is_parallel": true,
"self": 78.95513598707726
},
"communicator.exchange": {
"total": 1023.111021852003,
"count": 231990,
"is_parallel": true,
"self": 1023.111021852003
},
"steps_from_proto": {
"total": 85.88330033801071,
"count": 231990,
"is_parallel": true,
"self": 30.242043787950593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.64125655006012,
"count": 463980,
"is_parallel": true,
"self": 55.64125655006012
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.5267240839627,
"count": 231991,
"self": 6.151664333891517,
"children": {
"process_trajectory": {
"total": 152.33678919506974,
"count": 231991,
"self": 151.16622681406875,
"children": {
"RLTrainer._checkpoint": {
"total": 1.170562381000991,
"count": 10,
"self": 1.170562381000991
}
}
},
"_update_policy": {
"total": 323.0382705550014,
"count": 97,
"self": 259.3926169250158,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.645653629985645,
"count": 2910,
"self": 63.645653629985645
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.570000318286475e-07,
"count": 1,
"self": 8.570000318286475e-07
},
"TrainerController._save_models": {
"total": 0.1065459239998745,
"count": 1,
"self": 0.0015321419996325858,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10501378200024192,
"count": 1,
"self": 0.10501378200024192
}
}
}
}
}
}
}