ppo-Huggy / run_logs /timers.json
Juu24's picture
Huggy
142ef38 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4078866243362427,
"min": 1.4078866243362427,
"max": 1.4266791343688965,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70453.4609375,
"min": 68300.84375,
"max": 76347.21875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.02325581395348,
"min": 85.0051635111876,
"max": 390.4453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49548.0,
"min": 48900.0,
"max": 50182.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999357.0,
"min": 49761.0,
"max": 1999357.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999357.0,
"min": 49761.0,
"max": 1999357.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3928353786468506,
"min": 0.012409200891852379,
"max": 2.4398975372314453,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1232.3101806640625,
"min": 1.5759685039520264,
"max": 1416.1505126953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.694144558675081,
"min": 1.7175476778679946,
"max": 3.9147383954114976,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1902.4844477176666,
"min": 218.1285550892353,
"max": 2225.676259279251,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.694144558675081,
"min": 1.7175476778679946,
"max": 3.9147383954114976,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1902.4844477176666,
"min": 218.1285550892353,
"max": 2225.676259279251,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01617877920895504,
"min": 0.012726230735400652,
"max": 0.02037128494218147,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04853633762686513,
"min": 0.025452461470801303,
"max": 0.05423266124756386,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.049752598587009644,
"min": 0.024278128147125246,
"max": 0.05812748490522305,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14925779576102893,
"min": 0.04855625629425049,
"max": 0.172065415730079,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5036488321499997e-06,
"min": 3.5036488321499997e-06,
"max": 0.00029538247653917494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0510946496449999e-05,
"min": 1.0510946496449999e-05,
"max": 0.00084440896853035,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116785000000002,
"min": 0.10116785000000002,
"max": 0.19846082500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30350355000000007,
"min": 0.20751735,
"max": 0.5814696500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.8275715e-05,
"min": 6.8275715e-05,
"max": 0.0049231951675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020482714499999997,
"min": 0.00020482714499999997,
"max": 0.014075335534999999,
"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": "1727841809",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/juu/anaconda3/envs/drl2/bin/mlagents-learn ./ml-agents/config/ppo/Huggy.yaml --env=./ml-agents/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1727842551"
},
"total": 742.1194315829998,
"count": 1,
"self": 0.16608407199964859,
"children": {
"run_training.setup": {
"total": 0.01041912999971828,
"count": 1,
"self": 0.01041912999971828
},
"TrainerController.start_learning": {
"total": 741.9429283810005,
"count": 1,
"self": 1.7273088690035365,
"children": {
"TrainerController._reset_env": {
"total": 0.9325106329997652,
"count": 1,
"self": 0.9325106329997652
},
"TrainerController.advance": {
"total": 739.2428878349947,
"count": 232195,
"self": 1.618339914293756,
"children": {
"env_step": {
"total": 574.2060058125098,
"count": 232195,
"self": 438.0520501786086,
"children": {
"SubprocessEnvManager._take_step": {
"total": 135.00057818380083,
"count": 232195,
"self": 6.099773211386491,
"children": {
"TorchPolicy.evaluate": {
"total": 128.90080497241433,
"count": 222945,
"self": 128.90080497241433
}
}
},
"workers": {
"total": 1.153377450100379,
"count": 232195,
"self": 0.0,
"children": {
"worker_root": {
"total": 739.703753781514,
"count": 232195,
"is_parallel": true,
"self": 397.0949183150351,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0003279529992141761,
"count": 1,
"is_parallel": true,
"self": 9.230399882653728e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0002356490003876388,
"count": 2,
"is_parallel": true,
"self": 0.0002356490003876388
}
}
},
"UnityEnvironment.step": {
"total": 0.008563805000449065,
"count": 1,
"is_parallel": true,
"self": 8.870000056049321e-05,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.08000004326459e-05,
"count": 1,
"is_parallel": true,
"self": 8.08000004326459e-05
},
"communicator.exchange": {
"total": 0.00820098799886182,
"count": 1,
"is_parallel": true,
"self": 0.00820098799886182
},
"steps_from_proto": {
"total": 0.0001933170005941065,
"count": 1,
"is_parallel": true,
"self": 5.2198000048520043e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00014111900054558646,
"count": 2,
"is_parallel": true,
"self": 0.00014111900054558646
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 342.6088354664789,
"count": 232194,
"is_parallel": true,
"self": 10.173774753693579,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 19.182609677702203,
"count": 232194,
"is_parallel": true,
"self": 19.182609677702203
},
"communicator.exchange": {
"total": 289.4735462656354,
"count": 232194,
"is_parallel": true,
"self": 289.4735462656354
},
"steps_from_proto": {
"total": 23.778904769447763,
"count": 232194,
"is_parallel": true,
"self": 8.207082238495786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.571822530951977,
"count": 464388,
"is_parallel": true,
"self": 15.571822530951977
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 163.4185421081911,
"count": 232195,
"self": 2.6965878761202475,
"children": {
"process_trajectory": {
"total": 56.643000088077315,
"count": 232195,
"self": 56.12798819107593,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5150118970013864,
"count": 10,
"self": 0.5150118970013864
}
}
},
"_update_policy": {
"total": 104.07895414399354,
"count": 97,
"self": 86.59325066804013,
"children": {
"TorchPPOOptimizer.update": {
"total": 17.485703475953414,
"count": 2910,
"self": 17.485703475953414
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.210014594718814e-07,
"count": 1,
"self": 4.210014594718814e-07
},
"TrainerController._save_models": {
"total": 0.04022062300100515,
"count": 1,
"self": 0.0005989550008962397,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03962166800010891,
"count": 1,
"self": 0.03962166800010891
}
}
}
}
}
}
}