ppo-Huggy / run_logs /timers.json
ZhihongDeng's picture
Huggy
6075c52
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3995730876922607,
"min": 1.3995730876922607,
"max": 1.4258482456207275,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68131.21875,
"min": 68131.21875,
"max": 78160.4296875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.55,
"min": 85.44982698961938,
"max": 413.9586776859504,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49437.0,
"min": 49176.0,
"max": 50089.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999278.0,
"min": 49818.0,
"max": 1999278.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999278.0,
"min": 49818.0,
"max": 1999278.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4357705116271973,
"min": 0.07943582534790039,
"max": 2.4502010345458984,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1315.3160400390625,
"min": 9.532299041748047,
"max": 1370.743408203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7737838436056066,
"min": 1.9434644381205242,
"max": 3.8900357083018338,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2037.8432755470276,
"min": 233.2157325744629,
"max": 2167.2418056726456,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7737838436056066,
"min": 1.9434644381205242,
"max": 3.8900357083018338,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2037.8432755470276,
"min": 233.2157325744629,
"max": 2167.2418056726456,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01384708198408286,
"min": 0.01384708198408286,
"max": 0.019043820777005747,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.041541245952248576,
"min": 0.02926312863516311,
"max": 0.0564543234979889,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05336961042549875,
"min": 0.020982738025486468,
"max": 0.0587433494006594,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16010883127649625,
"min": 0.041965476050972936,
"max": 0.17557472561796506,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.280548906516656e-06,
"min": 3.280548906516656e-06,
"max": 0.0002953204515598499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.841646719549969e-06,
"min": 9.841646719549969e-06,
"max": 0.0008440158186613998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109348333333333,
"min": 0.10109348333333333,
"max": 0.19844014999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30328045,
"min": 0.20738315000000002,
"max": 0.5813386,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.456481833333319e-05,
"min": 6.456481833333319e-05,
"max": 0.0049221634850000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019369445499999957,
"min": 0.00019369445499999957,
"max": 0.01406879614,
"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": "1676598119",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676602736"
},
"total": 4617.910508485,
"count": 1,
"self": 0.6469052219999867,
"children": {
"run_training.setup": {
"total": 0.15609285700000441,
"count": 1,
"self": 0.15609285700000441
},
"TrainerController.start_learning": {
"total": 4617.107510406,
"count": 1,
"self": 7.597728260099757,
"children": {
"TrainerController._reset_env": {
"total": 11.073510975000005,
"count": 1,
"self": 11.073510975000005
},
"TrainerController.advance": {
"total": 4598.3084338929,
"count": 232125,
"self": 8.800705841133095,
"children": {
"env_step": {
"total": 2890.7260571618226,
"count": 232125,
"self": 2446.9538837179325,
"children": {
"SubprocessEnvManager._take_step": {
"total": 438.51055142904653,
"count": 232125,
"self": 28.27902807697791,
"children": {
"TorchPolicy.evaluate": {
"total": 410.2315233520686,
"count": 222822,
"self": 58.22945010597647,
"children": {
"TorchPolicy.sample_actions": {
"total": 352.00207324609215,
"count": 222822,
"self": 352.00207324609215
}
}
}
}
},
"workers": {
"total": 5.261622014843539,
"count": 232125,
"self": 0.0,
"children": {
"worker_root": {
"total": 4600.934915560897,
"count": 232125,
"is_parallel": true,
"self": 2643.5223162820066,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003001715000010563,
"count": 1,
"is_parallel": true,
"self": 0.00045834700000568773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025433680000048753,
"count": 2,
"is_parallel": true,
"self": 0.0025433680000048753
}
}
},
"UnityEnvironment.step": {
"total": 0.034461159000017005,
"count": 1,
"is_parallel": true,
"self": 0.0003797060000181318,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020901999999978216,
"count": 1,
"is_parallel": true,
"self": 0.00020901999999978216
},
"communicator.exchange": {
"total": 0.033013041000003795,
"count": 1,
"is_parallel": true,
"self": 0.033013041000003795
},
"steps_from_proto": {
"total": 0.0008593919999952959,
"count": 1,
"is_parallel": true,
"self": 0.000299552000001313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005598399999939829,
"count": 2,
"is_parallel": true,
"self": 0.0005598399999939829
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1957.4125992788906,
"count": 232124,
"is_parallel": true,
"self": 61.09194886792261,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.37744554694333,
"count": 232124,
"is_parallel": true,
"self": 92.37744554694333
},
"communicator.exchange": {
"total": 1661.0805253110989,
"count": 232124,
"is_parallel": true,
"self": 1661.0805253110989
},
"steps_from_proto": {
"total": 142.86267955292575,
"count": 232124,
"is_parallel": true,
"self": 54.635517185883145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 88.22716236704261,
"count": 464248,
"is_parallel": true,
"self": 88.22716236704261
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1698.781670889944,
"count": 232125,
"self": 13.145078059131265,
"children": {
"process_trajectory": {
"total": 268.46907641981295,
"count": 232125,
"self": 267.1434605728135,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3256158469994261,
"count": 10,
"self": 1.3256158469994261
}
}
},
"_update_policy": {
"total": 1417.167516411,
"count": 97,
"self": 382.9780500200011,
"children": {
"TorchPPOOptimizer.update": {
"total": 1034.1894663909989,
"count": 2910,
"self": 1034.1894663909989
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.840005077421665e-07,
"count": 1,
"self": 9.840005077421665e-07
},
"TrainerController._save_models": {
"total": 0.12783629399928031,
"count": 1,
"self": 0.006009398000060173,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12182689599922014,
"count": 1,
"self": 0.12182689599922014
}
}
}
}
}
}
}