ppo-Huggy / run_logs /timers.json
vumichien's picture
first commit
2307e56
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4021445512771606,
"min": 1.4021445512771606,
"max": 1.4272074699401855,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71099.9453125,
"min": 69115.71875,
"max": 77232.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.71513944223108,
"min": 81.92703150912106,
"max": 403.98387096774195,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49555.0,
"min": 48837.0,
"max": 50352.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999974.0,
"min": 49961.0,
"max": 1999974.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999974.0,
"min": 49961.0,
"max": 1999974.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.285369634628296,
"min": 0.1268167793750763,
"max": 2.449700117111206,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1147.255615234375,
"min": 15.59846305847168,
"max": 1437.877685546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.396677198281801,
"min": 1.9428809021062,
"max": 4.006137604120547,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1705.1319535374641,
"min": 238.97435095906258,
"max": 2301.5316302776337,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.396677198281801,
"min": 1.9428809021062,
"max": 4.006137604120547,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1705.1319535374641,
"min": 238.97435095906258,
"max": 2301.5316302776337,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015809591292499033,
"min": 0.014470061697233581,
"max": 0.01984073558220795,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0474287738774971,
"min": 0.029820115821106205,
"max": 0.054486708566158386,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04672870772580306,
"min": 0.022765385483702022,
"max": 0.0642589288867182,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14018612317740917,
"min": 0.045530770967404044,
"max": 0.19277678666015463,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.255848914750001e-06,
"min": 3.255848914750001e-06,
"max": 0.00029534955155014993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.767546744250004e-06,
"min": 9.767546744250004e-06,
"max": 0.00084396556867815,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108524999999997,
"min": 0.10108524999999997,
"max": 0.19844984999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30325574999999994,
"min": 0.20736449999999995,
"max": 0.58132185,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.415397500000003e-05,
"min": 6.415397500000003e-05,
"max": 0.004922647515,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019246192500000007,
"min": 0.00019246192500000007,
"max": 0.014067960315000001,
"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": "1685437208",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685439543"
},
"total": 2334.5775565450003,
"count": 1,
"self": 0.43949333000045954,
"children": {
"run_training.setup": {
"total": 0.04550117399998044,
"count": 1,
"self": 0.04550117399998044
},
"TrainerController.start_learning": {
"total": 2334.092562041,
"count": 1,
"self": 4.346734549999383,
"children": {
"TrainerController._reset_env": {
"total": 3.8555630769999993,
"count": 1,
"self": 3.8555630769999993
},
"TrainerController.advance": {
"total": 2325.7688241600003,
"count": 232287,
"self": 4.2472648888692675,
"children": {
"env_step": {
"total": 1810.7249937240863,
"count": 232287,
"self": 1525.6208358081647,
"children": {
"SubprocessEnvManager._take_step": {
"total": 282.4056056719283,
"count": 232287,
"self": 16.634621524941792,
"children": {
"TorchPolicy.evaluate": {
"total": 265.7709841469865,
"count": 223089,
"self": 265.7709841469865
}
}
},
"workers": {
"total": 2.6985522439933334,
"count": 232287,
"self": 0.0,
"children": {
"worker_root": {
"total": 2326.532594026039,
"count": 232287,
"is_parallel": true,
"self": 1080.6673355310204,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008963849999759077,
"count": 1,
"is_parallel": true,
"self": 0.0002580959999249899,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006382890000509178,
"count": 2,
"is_parallel": true,
"self": 0.0006382890000509178
}
}
},
"UnityEnvironment.step": {
"total": 0.02756687900000543,
"count": 1,
"is_parallel": true,
"self": 0.0003409939999414746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021720700004834725,
"count": 1,
"is_parallel": true,
"self": 0.00021720700004834725
},
"communicator.exchange": {
"total": 0.026217653000003338,
"count": 1,
"is_parallel": true,
"self": 0.026217653000003338
},
"steps_from_proto": {
"total": 0.0007910250000122687,
"count": 1,
"is_parallel": true,
"self": 0.0002474040000493005,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005436209999629682,
"count": 2,
"is_parallel": true,
"self": 0.0005436209999629682
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1245.8652584950187,
"count": 232286,
"is_parallel": true,
"self": 38.155171846074836,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.48660292702681,
"count": 232286,
"is_parallel": true,
"self": 76.48660292702681
},
"communicator.exchange": {
"total": 1040.941710252957,
"count": 232286,
"is_parallel": true,
"self": 1040.941710252957
},
"steps_from_proto": {
"total": 90.28177346896024,
"count": 232286,
"is_parallel": true,
"self": 32.835799230970565,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.445974237989674,
"count": 464572,
"is_parallel": true,
"self": 57.445974237989674
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 510.79656554704474,
"count": 232287,
"self": 6.424863266198258,
"children": {
"process_trajectory": {
"total": 132.92355401084626,
"count": 232287,
"self": 131.4985158588462,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4250381520000701,
"count": 10,
"self": 1.4250381520000701
}
}
},
"_update_policy": {
"total": 371.4481482700002,
"count": 97,
"self": 312.93178223800743,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.51636603199279,
"count": 2910,
"self": 58.51636603199279
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.85000042419415e-07,
"count": 1,
"self": 9.85000042419415e-07
},
"TrainerController._save_models": {
"total": 0.1214392689998931,
"count": 1,
"self": 0.002114439999786555,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11932482900010655,
"count": 1,
"self": 0.11932482900010655
}
}
}
}
}
}
}