ppo-Huggy / run_logs /timers.json
elvinado's picture
Huggy
791f78f
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4048640727996826,
"min": 1.4048640727996826,
"max": 1.4259699583053589,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69863.890625,
"min": 69588.359375,
"max": 74776.7890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 70.32952924393723,
"min": 70.32952924393723,
"max": 394.18897637795277,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49301.0,
"min": 48902.0,
"max": 50119.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999968.0,
"min": 49664.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999968.0,
"min": 49664.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.446587562561035,
"min": 0.1239025816321373,
"max": 2.537579298019409,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1715.057861328125,
"min": 15.611724853515625,
"max": 1725.58349609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.778713107024042,
"min": 1.8618319932193983,
"max": 4.066917097045664,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2648.8778880238533,
"min": 234.5908311456442,
"max": 2714.694901049137,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.778713107024042,
"min": 1.8618319932193983,
"max": 4.066917097045664,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2648.8778880238533,
"min": 234.5908311456442,
"max": 2714.694901049137,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016689289664565066,
"min": 0.012567483870467792,
"max": 0.020974521277821623,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0500678689936952,
"min": 0.025134967740935585,
"max": 0.05813443448860199,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0635361801005072,
"min": 0.021940076941003403,
"max": 0.0635361801005072,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1906085403015216,
"min": 0.043880153882006806,
"max": 0.1906085403015216,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8204487265499936e-06,
"min": 3.8204487265499936e-06,
"max": 0.00029531242656252493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.146134617964998e-05,
"min": 1.146134617964998e-05,
"max": 0.0008438827687057499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127344999999999,
"min": 0.10127344999999999,
"max": 0.198437475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30382034999999996,
"min": 0.20767734999999998,
"max": 0.5812942500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.354515499999991e-05,
"min": 7.354515499999991e-05,
"max": 0.004922030002499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022063546499999975,
"min": 0.00022063546499999975,
"max": 0.014066583075000002,
"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": "1682218986",
"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": "1682221575"
},
"total": 2588.580318793,
"count": 1,
"self": 0.43589609699984067,
"children": {
"run_training.setup": {
"total": 0.11250882899997805,
"count": 1,
"self": 0.11250882899997805
},
"TrainerController.start_learning": {
"total": 2588.031913867,
"count": 1,
"self": 5.145521320087028,
"children": {
"TrainerController._reset_env": {
"total": 3.9975804649999986,
"count": 1,
"self": 3.9975804649999986
},
"TrainerController.advance": {
"total": 2578.762118524913,
"count": 233324,
"self": 5.468321563965674,
"children": {
"env_step": {
"total": 2019.6752837629726,
"count": 233324,
"self": 1708.8207147938672,
"children": {
"SubprocessEnvManager._take_step": {
"total": 307.47752440097776,
"count": 233324,
"self": 18.21358454201379,
"children": {
"TorchPolicy.evaluate": {
"total": 289.26393985896397,
"count": 222928,
"self": 289.26393985896397
}
}
},
"workers": {
"total": 3.377044568127758,
"count": 233324,
"self": 0.0,
"children": {
"worker_root": {
"total": 2578.873114247885,
"count": 233324,
"is_parallel": true,
"self": 1182.4895395517801,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010162000000377702,
"count": 1,
"is_parallel": true,
"self": 0.00037177100000462815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006444290000331421,
"count": 2,
"is_parallel": true,
"self": 0.0006444290000331421
}
}
},
"UnityEnvironment.step": {
"total": 0.028269975999990038,
"count": 1,
"is_parallel": true,
"self": 0.0003192140000010113,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025632299997369046,
"count": 1,
"is_parallel": true,
"self": 0.00025632299997369046
},
"communicator.exchange": {
"total": 0.026979814000014812,
"count": 1,
"is_parallel": true,
"self": 0.026979814000014812
},
"steps_from_proto": {
"total": 0.0007146250000005239,
"count": 1,
"is_parallel": true,
"self": 0.00020830100004332053,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005063239999572033,
"count": 2,
"is_parallel": true,
"self": 0.0005063239999572033
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1396.383574696105,
"count": 233323,
"is_parallel": true,
"self": 41.61909943706178,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.91122631899276,
"count": 233323,
"is_parallel": true,
"self": 84.91122631899276
},
"communicator.exchange": {
"total": 1172.0617893999683,
"count": 233323,
"is_parallel": true,
"self": 1172.0617893999683
},
"steps_from_proto": {
"total": 97.79145954008209,
"count": 233323,
"is_parallel": true,
"self": 36.46191020922265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.329549330859436,
"count": 466646,
"is_parallel": true,
"self": 61.329549330859436
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 553.6185131979747,
"count": 233324,
"self": 8.111900918042352,
"children": {
"process_trajectory": {
"total": 146.59359251693235,
"count": 233324,
"self": 145.29048858793288,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3031039289994624,
"count": 10,
"self": 1.3031039289994624
}
}
},
"_update_policy": {
"total": 398.91301976299997,
"count": 97,
"self": 336.6156057270091,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.29741403599087,
"count": 2910,
"self": 62.29741403599087
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.82000074145617e-07,
"count": 1,
"self": 9.82000074145617e-07
},
"TrainerController._save_models": {
"total": 0.12669257500010644,
"count": 1,
"self": 0.004281556000023556,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12241101900008289,
"count": 1,
"self": 0.12241101900008289
}
}
}
}
}
}
}