ppo-Huggy / run_logs /timers.json
dlantonia's picture
Huggy
0423f04 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.409717082977295,
"min": 1.409717082977295,
"max": 1.4306895732879639,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71304.8984375,
"min": 68164.859375,
"max": 78229.4375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.24744027303754,
"min": 80.60848287112562,
"max": 383.53435114503816,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49369.0,
"min": 49098.0,
"max": 50243.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49625.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49625.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.416534185409546,
"min": 0.07566829770803452,
"max": 2.4614861011505127,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1416.0889892578125,
"min": 9.836878776550293,
"max": 1450.04443359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7382205961710766,
"min": 1.7787734580727723,
"max": 3.9580839296536787,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2190.5972693562508,
"min": 231.2405495494604,
"max": 2260.3556423187256,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7382205961710766,
"min": 1.7787734580727723,
"max": 3.9580839296536787,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2190.5972693562508,
"min": 231.2405495494604,
"max": 2260.3556423187256,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01599938201866785,
"min": 0.013008787294044546,
"max": 0.01950285962569372,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047998146056003554,
"min": 0.026017574588089093,
"max": 0.05850857887708116,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055351192545559674,
"min": 0.023205591334650916,
"max": 0.07121462859213351,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16605357763667902,
"min": 0.04641118266930183,
"max": 0.2004090754936139,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5541988153000045e-06,
"min": 3.5541988153000045e-06,
"max": 0.00029535990154669995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0662596445900013e-05,
"min": 1.0662596445900013e-05,
"max": 0.0008440813686395499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011847,
"min": 0.1011847,
"max": 0.1984533,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035541,
"min": 0.20750560000000007,
"max": 0.58136045,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.911653000000007e-05,
"min": 6.911653000000007e-05,
"max": 0.004922819670000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020734959000000023,
"min": 0.00020734959000000023,
"max": 0.014069886455,
"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": "1722692709",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722695165"
},
"total": 2456.228634949,
"count": 1,
"self": 0.4423120880001079,
"children": {
"run_training.setup": {
"total": 0.05674198300005173,
"count": 1,
"self": 0.05674198300005173
},
"TrainerController.start_learning": {
"total": 2455.729580878,
"count": 1,
"self": 4.545847621957364,
"children": {
"TrainerController._reset_env": {
"total": 2.8229928100000166,
"count": 1,
"self": 2.8229928100000166
},
"TrainerController.advance": {
"total": 2448.248647915043,
"count": 232510,
"self": 4.791008970936673,
"children": {
"env_step": {
"total": 1940.0015869401332,
"count": 232510,
"self": 1597.4941528771537,
"children": {
"SubprocessEnvManager._take_step": {
"total": 339.4781973489444,
"count": 232510,
"self": 17.989449981964526,
"children": {
"TorchPolicy.evaluate": {
"total": 321.48874736697985,
"count": 222978,
"self": 321.48874736697985
}
}
},
"workers": {
"total": 3.0292367140351644,
"count": 232510,
"self": 0.0,
"children": {
"worker_root": {
"total": 2448.1835789400784,
"count": 232510,
"is_parallel": true,
"self": 1161.437671291178,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009741230000486212,
"count": 1,
"is_parallel": true,
"self": 0.0002615220000734553,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007126009999751659,
"count": 2,
"is_parallel": true,
"self": 0.0007126009999751659
}
}
},
"UnityEnvironment.step": {
"total": 0.031769023999970614,
"count": 1,
"is_parallel": true,
"self": 0.0004141829999184665,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022346500003322944,
"count": 1,
"is_parallel": true,
"self": 0.00022346500003322944
},
"communicator.exchange": {
"total": 0.030267722000019148,
"count": 1,
"is_parallel": true,
"self": 0.030267722000019148
},
"steps_from_proto": {
"total": 0.0008636539999997694,
"count": 1,
"is_parallel": true,
"self": 0.0002212660000395772,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006423879999601922,
"count": 2,
"is_parallel": true,
"self": 0.0006423879999601922
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1286.7459076489004,
"count": 232509,
"is_parallel": true,
"self": 38.36809239098761,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.70810315897108,
"count": 232509,
"is_parallel": true,
"self": 84.70810315897108
},
"communicator.exchange": {
"total": 1071.7997949779192,
"count": 232509,
"is_parallel": true,
"self": 1071.7997949779192
},
"steps_from_proto": {
"total": 91.86991712102252,
"count": 232509,
"is_parallel": true,
"self": 34.4062886129247,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.46362850809783,
"count": 465018,
"is_parallel": true,
"self": 57.46362850809783
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.45605200397296,
"count": 232510,
"self": 6.903725854040829,
"children": {
"process_trajectory": {
"total": 164.16393110893046,
"count": 232510,
"self": 162.7435595689301,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4203715400003603,
"count": 10,
"self": 1.4203715400003603
}
}
},
"_update_policy": {
"total": 332.3883950410017,
"count": 97,
"self": 269.1500096250078,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.23838541599389,
"count": 2910,
"self": 63.23838541599389
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.339996722701471e-07,
"count": 1,
"self": 9.339996722701471e-07
},
"TrainerController._save_models": {
"total": 0.11209159700001692,
"count": 1,
"self": 0.0018599320001158048,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11023166499990111,
"count": 1,
"self": 0.11023166499990111
}
}
}
}
}
}
}