ppo-Huggy / run_logs /timers.json
code1phoenix's picture
Huggy
e27dd6a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066534042358398,
"min": 1.4066534042358398,
"max": 1.4308799505233765,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72438.4296875,
"min": 68671.3203125,
"max": 75617.7109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.47993579454254,
"min": 77.92222222222222,
"max": 396.3937007874016,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48893.0,
"min": 48893.0,
"max": 50342.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 49719.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 49719.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4877662658691406,
"min": 0.0639013722538948,
"max": 2.5088539123535156,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1552.3660888671875,
"min": 8.051572799682617,
"max": 1552.3660888671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.856583922337263,
"min": 1.720313208443778,
"max": 3.955006831615895,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2406.508367538452,
"min": 216.75946426391602,
"max": 2406.508367538452,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.856583922337263,
"min": 1.720313208443778,
"max": 3.955006831615895,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2406.508367538452,
"min": 216.75946426391602,
"max": 2406.508367538452,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016094185984628792,
"min": 0.013710037600443079,
"max": 0.019979629332859378,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.048282557953886376,
"min": 0.027420075200886157,
"max": 0.05734337695745732,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06687055428822836,
"min": 0.021475312827775875,
"max": 0.06687055428822836,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.20061166286468507,
"min": 0.04295062565555175,
"max": 0.20061166286468507,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4067488644499995e-06,
"min": 3.4067488644499995e-06,
"max": 0.00029527552657482493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0220246593349998e-05,
"min": 1.0220246593349998e-05,
"max": 0.0008437008187663999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113555,
"min": 0.10113555,
"max": 0.19842517499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30340665,
"min": 0.20741849999999995,
"max": 0.5812336000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.6663945e-05,
"min": 6.6663945e-05,
"max": 0.004921416232499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000199991835,
"min": 0.000199991835,
"max": 0.014063556640000002,
"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": "1773782512",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1773785194"
},
"total": 2681.6469914789996,
"count": 1,
"self": 0.4396340899993447,
"children": {
"run_training.setup": {
"total": 0.025880426000185253,
"count": 1,
"self": 0.025880426000185253
},
"TrainerController.start_learning": {
"total": 2681.181476963,
"count": 1,
"self": 4.4520147179368905,
"children": {
"TrainerController._reset_env": {
"total": 2.820648789000188,
"count": 1,
"self": 2.820648789000188
},
"TrainerController.advance": {
"total": 2673.8099589940625,
"count": 232622,
"self": 4.4982353108239295,
"children": {
"env_step": {
"total": 2193.3574965181324,
"count": 232622,
"self": 1769.5321024862208,
"children": {
"SubprocessEnvManager._take_step": {
"total": 421.000972651982,
"count": 232622,
"self": 16.034350682871036,
"children": {
"TorchPolicy.evaluate": {
"total": 404.966621969111,
"count": 223045,
"self": 404.966621969111
}
}
},
"workers": {
"total": 2.8244213799296176,
"count": 232622,
"self": 0.0,
"children": {
"worker_root": {
"total": 2668.2299863719413,
"count": 232622,
"is_parallel": true,
"self": 1235.2980324639304,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008051009999689995,
"count": 1,
"is_parallel": true,
"self": 0.00021663699999407982,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005884639999749197,
"count": 2,
"is_parallel": true,
"self": 0.0005884639999749197
}
}
},
"UnityEnvironment.step": {
"total": 0.03101282500006164,
"count": 1,
"is_parallel": true,
"self": 0.0003055380000205332,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019542599989108567,
"count": 1,
"is_parallel": true,
"self": 0.00019542599989108567
},
"communicator.exchange": {
"total": 0.029739340000105585,
"count": 1,
"is_parallel": true,
"self": 0.029739340000105585
},
"steps_from_proto": {
"total": 0.0007725210000444349,
"count": 1,
"is_parallel": true,
"self": 0.00019768000015574216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005748409998886927,
"count": 2,
"is_parallel": true,
"self": 0.0005748409998886927
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1432.9319539080109,
"count": 232621,
"is_parallel": true,
"self": 39.70281036168376,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.6591371611612,
"count": 232621,
"is_parallel": true,
"self": 87.6591371611612
},
"communicator.exchange": {
"total": 1211.7471581389832,
"count": 232621,
"is_parallel": true,
"self": 1211.7471581389832
},
"steps_from_proto": {
"total": 93.82284824618273,
"count": 232621,
"is_parallel": true,
"self": 33.81709837120411,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.00574987497862,
"count": 465242,
"is_parallel": true,
"self": 60.00574987497862
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 475.954227165106,
"count": 232622,
"self": 6.634524476110528,
"children": {
"process_trajectory": {
"total": 162.93168959199738,
"count": 232622,
"self": 161.80949440799736,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1221951840000202,
"count": 10,
"self": 1.1221951840000202
}
}
},
"_update_policy": {
"total": 306.38801309699807,
"count": 97,
"self": 242.84235806099264,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.54565503600543,
"count": 2910,
"self": 63.54565503600543
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.500001058564521e-07,
"count": 1,
"self": 8.500001058564521e-07
},
"TrainerController._save_models": {
"total": 0.09885361200031184,
"count": 1,
"self": 0.0012958580000486108,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09755775400026323,
"count": 1,
"self": 0.09755775400026323
}
}
}
}
}
}
}