ppo-Huggy / run_logs /timers.json
RedPandaBoy's picture
Huggy
92aee26 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.382308840751648,
"min": 1.382308840751648,
"max": 1.4185924530029297,
"count": 12
},
"Huggy.Policy.Entropy.sum": {
"value": 69541.1953125,
"min": 68559.796875,
"max": 76501.28125,
"count": 12
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 113.82876712328768,
"min": 113.82876712328768,
"max": 406.8536585365854,
"count": 12
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49857.0,
"min": 49089.0,
"max": 50115.0,
"count": 12
},
"Huggy.Step.mean": {
"value": 599567.0,
"min": 49539.0,
"max": 599567.0,
"count": 12
},
"Huggy.Step.sum": {
"value": 599567.0,
"min": 49539.0,
"max": 599567.0,
"count": 12
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.845660924911499,
"min": 0.026145128533244133,
"max": 1.845660924911499,
"count": 12
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 808.3994750976562,
"min": 3.1897056102752686,
"max": 808.3994750976562,
"count": 12
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6355882142776768,
"min": 1.7491514431160005,
"max": 3.7201078874724254,
"count": 12
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1592.3876378536224,
"min": 213.39647606015205,
"max": 1592.3876378536224,
"count": 12
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6355882142776768,
"min": 1.7491514431160005,
"max": 3.7201078874724254,
"count": 12
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1592.3876378536224,
"min": 213.39647606015205,
"max": 1592.3876378536224,
"count": 12
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019637240868824946,
"min": 0.015420571969783244,
"max": 0.020822764120142286,
"count": 12
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05891172260647484,
"min": 0.03084114393956649,
"max": 0.06057357656633637,
"count": 12
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03335966654121875,
"min": 0.020966059683511652,
"max": 0.08619314562529325,
"count": 12
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10007899962365627,
"min": 0.041932119367023304,
"max": 0.1723862912505865,
"count": 12
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.00035571044552458334,
"min": 0.00035571044552458334,
"max": 0.0004921675015665001,
"count": 12
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.00106713133657375,
"min": 0.0007370898025820498,
"max": 0.0014068332686333494,
"count": 12
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.17114208333333333,
"min": 0.17114208333333333,
"max": 0.19843350000000004,
"count": 12
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.51342625,
"min": 0.3474179500000001,
"max": 0.5813666499999999,
"count": 12
},
"Huggy.Policy.Beta.mean": {
"value": 0.0035599899583333345,
"min": 0.0035599899583333345,
"max": 0.00492183165,
"count": 12
},
"Huggy.Policy.Beta.sum": {
"value": 0.010679969875000004,
"min": 0.007376155705,
"max": 0.014070195835,
"count": 12
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 12
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 12
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1748472665",
"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=Huggy3 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748473424"
},
"total": 759.116876738,
"count": 1,
"self": 0.43280477899998004,
"children": {
"run_training.setup": {
"total": 0.023299514999962412,
"count": 1,
"self": 0.023299514999962412
},
"TrainerController.start_learning": {
"total": 758.660772444,
"count": 1,
"self": 1.3549806460259788,
"children": {
"TrainerController._reset_env": {
"total": 2.249835361000123,
"count": 1,
"self": 2.249835361000123
},
"TrainerController.advance": {
"total": 755.052911431974,
"count": 70912,
"self": 1.4579743318493001,
"children": {
"env_step": {
"total": 604.9785082271101,
"count": 70912,
"self": 472.1224253330888,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.06185703299752,
"count": 70912,
"self": 4.9482572350580085,
"children": {
"TorchPolicy.evaluate": {
"total": 127.11359979793951,
"count": 69091,
"self": 127.11359979793951
}
}
},
"workers": {
"total": 0.7942258610237332,
"count": 70911,
"self": 0.0,
"children": {
"worker_root": {
"total": 756.5236228890171,
"count": 70911,
"is_parallel": true,
"self": 371.1524579859904,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008947759999955451,
"count": 1,
"is_parallel": true,
"self": 0.00026213700016342045,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006326389998321247,
"count": 2,
"is_parallel": true,
"self": 0.0006326389998321247
}
}
},
"UnityEnvironment.step": {
"total": 0.030743139999913183,
"count": 1,
"is_parallel": true,
"self": 0.0002640019999944343,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019860799989146471,
"count": 1,
"is_parallel": true,
"self": 0.00019860799989146471
},
"communicator.exchange": {
"total": 0.0277933209999901,
"count": 1,
"is_parallel": true,
"self": 0.0277933209999901
},
"steps_from_proto": {
"total": 0.0024872090000371827,
"count": 1,
"is_parallel": true,
"self": 0.00017187299999932293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023153360000378598,
"count": 2,
"is_parallel": true,
"self": 0.0023153360000378598
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 385.37116490302674,
"count": 70910,
"is_parallel": true,
"self": 11.232702368989067,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.937112903997104,
"count": 70910,
"is_parallel": true,
"self": 24.937112903997104
},
"communicator.exchange": {
"total": 322.83634771399556,
"count": 70910,
"is_parallel": true,
"self": 322.83634771399556
},
"steps_from_proto": {
"total": 26.365001916045003,
"count": 70910,
"is_parallel": true,
"self": 9.279736069046294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.08526584699871,
"count": 141820,
"is_parallel": true,
"self": 17.08526584699871
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 148.61642887301468,
"count": 70911,
"self": 2.0986273839939713,
"children": {
"process_trajectory": {
"total": 42.858607027020525,
"count": 70911,
"self": 41.99118007302036,
"children": {
"RLTrainer._checkpoint": {
"total": 0.867426954000166,
"count": 3,
"self": 0.867426954000166
}
}
},
"_update_policy": {
"total": 103.65919446200019,
"count": 29,
"self": 75.56046004699465,
"children": {
"TorchPPOOptimizer.update": {
"total": 28.098734415005538,
"count": 870,
"self": 28.098734415005538
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.151000105892308e-06,
"count": 1,
"self": 1.151000105892308e-06
},
"TrainerController._save_models": {
"total": 0.003043853999770363,
"count": 1,
"self": 2.4092999410640914e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.003019761000359722,
"count": 1,
"self": 0.003019761000359722
}
}
}
}
}
}
}