ppo-Huggy / run_logs /timers.json
greatwind's picture
Huggy
82d3823 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4101488590240479,
"min": 1.4101488590240479,
"max": 1.4292985200881958,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70472.1875,
"min": 69269.984375,
"max": 78127.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.41287284144427,
"min": 72.27525622254758,
"max": 380.6793893129771,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49312.0,
"min": 48816.0,
"max": 49967.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49658.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49658.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5102505683898926,
"min": 0.23717442154884338,
"max": 2.5406641960144043,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1599.029541015625,
"min": 30.832674026489258,
"max": 1705.8994140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8861802138937884,
"min": 1.8355110042370282,
"max": 4.05464485282973,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2475.4967962503433,
"min": 238.61643055081367,
"max": 2690.7162302732468,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8861802138937884,
"min": 1.8355110042370282,
"max": 4.05464485282973,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2475.4967962503433,
"min": 238.61643055081367,
"max": 2690.7162302732468,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018149612074355698,
"min": 0.013213088648869113,
"max": 0.02133750255485817,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05444883622306709,
"min": 0.026426177297738225,
"max": 0.05686321361766507,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057087529492047095,
"min": 0.019933512015268204,
"max": 0.05839832816272974,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1712625884761413,
"min": 0.03986702403053641,
"max": 0.17206839186449846,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.771798742766666e-06,
"min": 3.771798742766666e-06,
"max": 0.00029535165154944993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1315396228299998e-05,
"min": 1.1315396228299998e-05,
"max": 0.0008441611686129497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125723333333332,
"min": 0.10125723333333332,
"max": 0.19845055,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037717,
"min": 0.20770125,
"max": 0.5813870500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.273594333333334e-05,
"min": 7.273594333333334e-05,
"max": 0.004922682445,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021820783,
"min": 0.00021820783,
"max": 0.014071213795000002,
"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": "1749365591",
"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": "1749368393"
},
"total": 2801.403079941,
"count": 1,
"self": 0.4906135130004259,
"children": {
"run_training.setup": {
"total": 0.026656240999955116,
"count": 1,
"self": 0.026656240999955116
},
"TrainerController.start_learning": {
"total": 2800.885810187,
"count": 1,
"self": 5.012679981945894,
"children": {
"TrainerController._reset_env": {
"total": 3.7555393840000306,
"count": 1,
"self": 3.7555393840000306
},
"TrainerController.advance": {
"total": 2791.991987622054,
"count": 233690,
"self": 5.622028041232625,
"children": {
"env_step": {
"total": 2249.9492535768495,
"count": 233690,
"self": 1761.3224487108798,
"children": {
"SubprocessEnvManager._take_step": {
"total": 485.4675952019736,
"count": 233690,
"self": 17.791198551112984,
"children": {
"TorchPolicy.evaluate": {
"total": 467.6763966508606,
"count": 223001,
"self": 467.6763966508606
}
}
},
"workers": {
"total": 3.15920966399608,
"count": 233690,
"self": 0.0,
"children": {
"worker_root": {
"total": 2792.9001918779545,
"count": 233690,
"is_parallel": true,
"self": 1356.3110869309942,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010821420000866055,
"count": 1,
"is_parallel": true,
"self": 0.0002810210000916413,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008011209999949642,
"count": 2,
"is_parallel": true,
"self": 0.0008011209999949642
}
}
},
"UnityEnvironment.step": {
"total": 0.05159626299996489,
"count": 1,
"is_parallel": true,
"self": 0.00031519499998466927,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023276800015992194,
"count": 1,
"is_parallel": true,
"self": 0.00023276800015992194
},
"communicator.exchange": {
"total": 0.05033166899988828,
"count": 1,
"is_parallel": true,
"self": 0.05033166899988828
},
"steps_from_proto": {
"total": 0.000716630999932022,
"count": 1,
"is_parallel": true,
"self": 0.00018497900009606383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005316519998359581,
"count": 2,
"is_parallel": true,
"self": 0.0005316519998359581
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1436.5891049469603,
"count": 233689,
"is_parallel": true,
"self": 41.24756917573745,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 95.51552629108369,
"count": 233689,
"is_parallel": true,
"self": 95.51552629108369
},
"communicator.exchange": {
"total": 1200.5768602650417,
"count": 233689,
"is_parallel": true,
"self": 1200.5768602650417
},
"steps_from_proto": {
"total": 99.24914921509753,
"count": 233689,
"is_parallel": true,
"self": 37.882689614993296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.366459600104236,
"count": 467378,
"is_parallel": true,
"self": 61.366459600104236
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 536.4207060039719,
"count": 233690,
"self": 7.334659053930636,
"children": {
"process_trajectory": {
"total": 195.89493033704025,
"count": 233690,
"self": 194.5565277040405,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3384026329997596,
"count": 10,
"self": 1.3384026329997596
}
}
},
"_update_policy": {
"total": 333.191116613001,
"count": 97,
"self": 265.71825604799915,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.47286056500184,
"count": 2910,
"self": 67.47286056500184
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2010000318696257e-06,
"count": 1,
"self": 1.2010000318696257e-06
},
"TrainerController._save_models": {
"total": 0.12560199800009286,
"count": 1,
"self": 0.0021372679998421518,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12346473000025071,
"count": 1,
"self": 0.12346473000025071
}
}
}
}
}
}
}