ppo-Huggy / run_logs /timers.json
Samini10's picture
Huggy
9757d8a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406200885772705,
"min": 1.406200885772705,
"max": 1.428224802017212,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70426.7578125,
"min": 69181.171875,
"max": 77543.8828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.70483870967742,
"min": 71.35455861070912,
"max": 384.1526717557252,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49417.0,
"min": 49271.0,
"max": 50324.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999997.0,
"min": 49705.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999997.0,
"min": 49705.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.483088254928589,
"min": 0.10676486045122147,
"max": 2.5057785511016846,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1539.5146484375,
"min": 13.87943172454834,
"max": 1698.0848388671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8635001121990142,
"min": 1.9189761647811303,
"max": 4.048758151224165,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2395.370069563389,
"min": 249.46690142154694,
"max": 2702.454507946968,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8635001121990142,
"min": 1.9189761647811303,
"max": 4.048758151224165,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2395.370069563389,
"min": 249.46690142154694,
"max": 2702.454507946968,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018033390095742004,
"min": 0.013720948744836883,
"max": 0.019398761086631567,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05410017028722602,
"min": 0.027441897489673767,
"max": 0.0581962832598947,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052146931240955985,
"min": 0.022887199465185405,
"max": 0.06129417630533378,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15644079372286795,
"min": 0.04577439893037081,
"max": 0.1790765097985665,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.93829868726667e-06,
"min": 3.93829868726667e-06,
"max": 0.00029532202655932493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.181489606180001e-05,
"min": 1.181489606180001e-05,
"max": 0.00084395686868105,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131273333333334,
"min": 0.10131273333333334,
"max": 0.198440675,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039382,
"min": 0.20775815000000003,
"max": 0.5813189500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.550539333333342e-05,
"min": 7.550539333333342e-05,
"max": 0.004922189682499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022651618000000027,
"min": 0.00022651618000000027,
"max": 0.014067815605000002,
"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": "1753729342",
"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": "1753733632"
},
"total": 4290.168886341,
"count": 1,
"self": 0.8685637890002909,
"children": {
"run_training.setup": {
"total": 0.0572414129999288,
"count": 1,
"self": 0.0572414129999288
},
"TrainerController.start_learning": {
"total": 4289.2430811389995,
"count": 1,
"self": 7.63175728081751,
"children": {
"TrainerController._reset_env": {
"total": 4.665957785000046,
"count": 1,
"self": 4.665957785000046
},
"TrainerController.advance": {
"total": 4276.788822293182,
"count": 233451,
"self": 8.17584444795284,
"children": {
"env_step": {
"total": 2825.4182515512084,
"count": 233451,
"self": 2373.1016012122163,
"children": {
"SubprocessEnvManager._take_step": {
"total": 447.24367568206344,
"count": 233451,
"self": 28.008825405072002,
"children": {
"TorchPolicy.evaluate": {
"total": 419.23485027699144,
"count": 222975,
"self": 419.23485027699144
}
}
},
"workers": {
"total": 5.072974656928636,
"count": 233451,
"self": 0.0,
"children": {
"worker_root": {
"total": 4276.24302946792,
"count": 233451,
"is_parallel": true,
"self": 2372.3219366937974,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013140239998392644,
"count": 1,
"is_parallel": true,
"self": 0.00041244700014431146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000901576999694953,
"count": 2,
"is_parallel": true,
"self": 0.000901576999694953
}
}
},
"UnityEnvironment.step": {
"total": 0.03919214699999429,
"count": 1,
"is_parallel": true,
"self": 0.00046529699989150686,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002437559999179939,
"count": 1,
"is_parallel": true,
"self": 0.0002437559999179939
},
"communicator.exchange": {
"total": 0.03755517800004782,
"count": 1,
"is_parallel": true,
"self": 0.03755517800004782
},
"steps_from_proto": {
"total": 0.0009279160001369746,
"count": 1,
"is_parallel": true,
"self": 0.0002439080001295224,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006840080000074522,
"count": 2,
"is_parallel": true,
"self": 0.0006840080000074522
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1903.9210927741224,
"count": 233450,
"is_parallel": true,
"self": 59.25450827622444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 108.95139951696615,
"count": 233450,
"is_parallel": true,
"self": 108.95139951696615
},
"communicator.exchange": {
"total": 1603.9739207599926,
"count": 233450,
"is_parallel": true,
"self": 1603.9739207599926
},
"steps_from_proto": {
"total": 131.74126422093923,
"count": 233450,
"is_parallel": true,
"self": 42.85214923880039,
"children": {
"_process_rank_one_or_two_observation": {
"total": 88.88911498213884,
"count": 466900,
"is_parallel": true,
"self": 88.88911498213884
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1443.1947262940212,
"count": 233451,
"self": 11.552163381124046,
"children": {
"process_trajectory": {
"total": 248.13545667790095,
"count": 233451,
"self": 246.8986029258997,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2368537520012524,
"count": 10,
"self": 1.2368537520012524
}
}
},
"_update_policy": {
"total": 1183.5071062349962,
"count": 97,
"self": 314.53387674798796,
"children": {
"TorchPPOOptimizer.update": {
"total": 868.9732294870082,
"count": 2910,
"self": 868.9732294870082
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.314000655838754e-06,
"count": 1,
"self": 1.314000655838754e-06
},
"TrainerController._save_models": {
"total": 0.15654246599933686,
"count": 1,
"self": 0.010911946999840438,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14563051899949642,
"count": 1,
"self": 0.14563051899949642
}
}
}
}
}
}
}