ppo-Huggy / run_logs /timers.json
dawoz's picture
Huggy
139fbaa
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4072926044464111,
"min": 1.4072926044464111,
"max": 1.4291212558746338,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71587.5703125,
"min": 68925.609375,
"max": 77273.1328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 108.94469026548673,
"min": 90.51465201465201,
"max": 423.85593220338984,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49243.0,
"min": 48909.0,
"max": 50418.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999964.0,
"min": 49516.0,
"max": 1999964.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999964.0,
"min": 49516.0,
"max": 1999964.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.373324394226074,
"min": 0.15335574746131897,
"max": 2.40364670753479,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1072.74267578125,
"min": 17.942623138427734,
"max": 1302.6441650390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.638984130942716,
"min": 1.7939770743887649,
"max": 3.861125403267192,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1644.8208271861076,
"min": 209.8953177034855,
"max": 2016.1896228194237,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.638984130942716,
"min": 1.7939770743887649,
"max": 3.861125403267192,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1644.8208271861076,
"min": 209.8953177034855,
"max": 2016.1896228194237,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01874696219003656,
"min": 0.013889692260757631,
"max": 0.02116120544972849,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05624088657010967,
"min": 0.027779384521515262,
"max": 0.05665810870705172,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.043438596237036914,
"min": 0.020955988237013418,
"max": 0.05608197624484698,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13031578871111074,
"min": 0.041911976474026835,
"max": 0.16824592873454094,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.0992989669333346e-06,
"min": 3.0992989669333346e-06,
"max": 0.00029535457654847504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.297896900800004e-06,
"min": 9.297896900800004e-06,
"max": 0.0008440777686407497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10103306666666667,
"min": 0.10103306666666667,
"max": 0.19845152499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3030992,
"min": 0.20720079999999996,
"max": 0.5813592499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.155002666666671e-05,
"min": 6.155002666666671e-05,
"max": 0.004922731097500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018465008000000013,
"min": 0.00018465008000000013,
"max": 0.014069826575,
"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": "1683292251",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683294933"
},
"total": 2681.821430687,
"count": 1,
"self": 0.8012668630003645,
"children": {
"run_training.setup": {
"total": 0.03958268800005271,
"count": 1,
"self": 0.03958268800005271
},
"TrainerController.start_learning": {
"total": 2680.9805811359997,
"count": 1,
"self": 4.8606919100434425,
"children": {
"TrainerController._reset_env": {
"total": 4.457031008000001,
"count": 1,
"self": 4.457031008000001
},
"TrainerController.advance": {
"total": 2671.446970764957,
"count": 231543,
"self": 5.075776531000429,
"children": {
"env_step": {
"total": 2099.7035644459343,
"count": 231543,
"self": 1777.1413481649636,
"children": {
"SubprocessEnvManager._take_step": {
"total": 319.32931630503526,
"count": 231543,
"self": 18.42994445215203,
"children": {
"TorchPolicy.evaluate": {
"total": 300.89937185288323,
"count": 223093,
"self": 300.89937185288323
}
}
},
"workers": {
"total": 3.232899975935368,
"count": 231543,
"self": 0.0,
"children": {
"worker_root": {
"total": 2672.0738125829603,
"count": 231543,
"is_parallel": true,
"self": 1222.0705726199765,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007067970000207424,
"count": 1,
"is_parallel": true,
"self": 0.0002239060000306381,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004828909999901043,
"count": 2,
"is_parallel": true,
"self": 0.0004828909999901043
}
}
},
"UnityEnvironment.step": {
"total": 0.07876232400002436,
"count": 1,
"is_parallel": true,
"self": 0.00031890500002873523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021467400000574344,
"count": 1,
"is_parallel": true,
"self": 0.00021467400000574344
},
"communicator.exchange": {
"total": 0.07753202999998621,
"count": 1,
"is_parallel": true,
"self": 0.07753202999998621
},
"steps_from_proto": {
"total": 0.0006967150000036781,
"count": 1,
"is_parallel": true,
"self": 0.00020328299996208443,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004934320000415937,
"count": 2,
"is_parallel": true,
"self": 0.0004934320000415937
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1450.0032399629838,
"count": 231542,
"is_parallel": true,
"self": 42.03326600402147,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.80642658895681,
"count": 231542,
"is_parallel": true,
"self": 89.80642658895681
},
"communicator.exchange": {
"total": 1216.3201770869864,
"count": 231542,
"is_parallel": true,
"self": 1216.3201770869864
},
"steps_from_proto": {
"total": 101.84337028301911,
"count": 231542,
"is_parallel": true,
"self": 39.85318968002889,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.99018060299022,
"count": 463084,
"is_parallel": true,
"self": 61.99018060299022
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 566.6676297880222,
"count": 231543,
"self": 7.393289194122531,
"children": {
"process_trajectory": {
"total": 147.7177334149004,
"count": 231543,
"self": 146.14475445190078,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5729789629996276,
"count": 10,
"self": 1.5729789629996276
}
}
},
"_update_policy": {
"total": 411.55660717899923,
"count": 97,
"self": 349.3256616230018,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.23094555599744,
"count": 2910,
"self": 62.23094555599744
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.469999915570952e-06,
"count": 1,
"self": 1.469999915570952e-06
},
"TrainerController._save_models": {
"total": 0.21588598299967998,
"count": 1,
"self": 0.0032860369997251837,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2125999459999548,
"count": 1,
"self": 0.2125999459999548
}
}
}
}
}
}
}