ppo-Huggy / run_logs /timers.json
Simple-Chop's picture
Huggy
b2303ce verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3993810415267944,
"min": 1.3993810415267944,
"max": 1.4314305782318115,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70155.171875,
"min": 68900.34375,
"max": 75764.5390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.9888178913738,
"min": 72.46029411764705,
"max": 405.5365853658537,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49447.0,
"min": 49132.0,
"max": 50062.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49386.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49386.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4049394130706787,
"min": 0.2220151126384735,
"max": 2.5060055255889893,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1505.4920654296875,
"min": 27.085844039916992,
"max": 1619.7958984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6705245763158647,
"min": 1.6650458435054685,
"max": 4.0741453804889645,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2297.7483847737312,
"min": 203.13559290766716,
"max": 2554.136534333229,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6705245763158647,
"min": 1.6650458435054685,
"max": 4.0741453804889645,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2297.7483847737312,
"min": 203.13559290766716,
"max": 2554.136534333229,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015375058101845853,
"min": 0.014340275024490742,
"max": 0.019572732609231026,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04612517430553756,
"min": 0.028680550048981485,
"max": 0.05764382160171712,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05247593224048614,
"min": 0.02129006023622221,
"max": 0.07790482118725778,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15742779672145843,
"min": 0.04399685425062974,
"max": 0.2118373829871416,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.662798779099996e-06,
"min": 3.662798779099996e-06,
"max": 0.00029528895157034996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0988396337299987e-05,
"min": 1.0988396337299987e-05,
"max": 0.0008438713687095498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122089999999999,
"min": 0.10122089999999999,
"max": 0.19842965,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30366269999999995,
"min": 0.20756989999999997,
"max": 0.58129045,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.092290999999995e-05,
"min": 7.092290999999995e-05,
"max": 0.004921639535000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021276872999999985,
"min": 0.00021276872999999985,
"max": 0.014066393455000003,
"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": "1741310768",
"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=Huggy1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741313175"
},
"total": 2407.0663092249997,
"count": 1,
"self": 0.43785373099990466,
"children": {
"run_training.setup": {
"total": 0.03669205200003489,
"count": 1,
"self": 0.03669205200003489
},
"TrainerController.start_learning": {
"total": 2406.591763442,
"count": 1,
"self": 4.181948400032979,
"children": {
"TrainerController._reset_env": {
"total": 3.078418237999813,
"count": 1,
"self": 3.078418237999813
},
"TrainerController.advance": {
"total": 2399.216522235967,
"count": 233003,
"self": 4.0922540048195515,
"children": {
"env_step": {
"total": 1889.5019177830363,
"count": 233003,
"self": 1477.0992264691067,
"children": {
"SubprocessEnvManager._take_step": {
"total": 409.9189736569324,
"count": 233003,
"self": 14.908273489843623,
"children": {
"TorchPolicy.evaluate": {
"total": 395.01070016708877,
"count": 222960,
"self": 395.01070016708877
}
}
},
"workers": {
"total": 2.4837176569972144,
"count": 233003,
"self": 0.0,
"children": {
"worker_root": {
"total": 2399.559458981969,
"count": 233003,
"is_parallel": true,
"self": 1190.9028935788413,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00102395399994748,
"count": 1,
"is_parallel": true,
"self": 0.00038985299988780753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006341010000596725,
"count": 2,
"is_parallel": true,
"self": 0.0006341010000596725
}
}
},
"UnityEnvironment.step": {
"total": 0.02823729000010644,
"count": 1,
"is_parallel": true,
"self": 0.0003308300001663156,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001946830000179034,
"count": 1,
"is_parallel": true,
"self": 0.0001946830000179034
},
"communicator.exchange": {
"total": 0.027022267999882388,
"count": 1,
"is_parallel": true,
"self": 0.027022267999882388
},
"steps_from_proto": {
"total": 0.0006895090000398341,
"count": 1,
"is_parallel": true,
"self": 0.00019944700011365057,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004900619999261835,
"count": 2,
"is_parallel": true,
"self": 0.0004900619999261835
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1208.6565654031276,
"count": 233002,
"is_parallel": true,
"self": 36.59367742882205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.8943986652423,
"count": 233002,
"is_parallel": true,
"self": 78.8943986652423
},
"communicator.exchange": {
"total": 1009.1747286479119,
"count": 233002,
"is_parallel": true,
"self": 1009.1747286479119
},
"steps_from_proto": {
"total": 83.99376066115133,
"count": 233002,
"is_parallel": true,
"self": 29.462473124014423,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.531287537136905,
"count": 466004,
"is_parallel": true,
"self": 54.531287537136905
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.62235044811155,
"count": 233003,
"self": 6.147013459015852,
"children": {
"process_trajectory": {
"total": 159.99088414509856,
"count": 233003,
"self": 158.76028663609804,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2305975090005177,
"count": 10,
"self": 1.2305975090005177
}
}
},
"_update_policy": {
"total": 339.48445284399713,
"count": 97,
"self": 272.93885595599386,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.54559688800327,
"count": 2910,
"self": 66.54559688800327
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.829999049135949e-07,
"count": 1,
"self": 7.829999049135949e-07
},
"TrainerController._save_models": {
"total": 0.11487378499987244,
"count": 1,
"self": 0.002112892999775795,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11276089200009665,
"count": 1,
"self": 0.11276089200009665
}
}
}
}
}
}
}