ppo-Huggy / run_logs /timers.json
averydd's picture
Huggy
5e55946 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.399357795715332,
"min": 1.399357795715332,
"max": 1.4269315004348755,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69515.8984375,
"min": 68373.9765625,
"max": 78869.9140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 118.90799031476998,
"min": 87.73179396092362,
"max": 407.7983870967742,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49109.0,
"min": 48985.0,
"max": 50567.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49941.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49941.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.308913469314575,
"min": 0.030281618237495422,
"max": 2.4797985553741455,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 953.581298828125,
"min": 3.7246389389038086,
"max": 1378.9227294921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4087503996946045,
"min": 1.842528354588563,
"max": 3.8714479884322808,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1407.8139150738716,
"min": 226.63098761439323,
"max": 2153.2529659867287,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4087503996946045,
"min": 1.842528354588563,
"max": 3.8714479884322808,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1407.8139150738716,
"min": 226.63098761439323,
"max": 2153.2529659867287,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017290950520287476,
"min": 0.014022070570111584,
"max": 0.020018754550255834,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051872851560862424,
"min": 0.028044141140223168,
"max": 0.056393893601853054,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03955698915653759,
"min": 0.021723322632412116,
"max": 0.06781915556639433,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11867096746961277,
"min": 0.04344664526482423,
"max": 0.18507973315815132,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3703988765666702e-06,
"min": 3.3703988765666702e-06,
"max": 0.0002953493265502249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.011119662970001e-05,
"min": 1.011119662970001e-05,
"max": 0.0008441253186248998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112343333333335,
"min": 0.10112343333333335,
"max": 0.198449775,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30337030000000004,
"min": 0.20741995000000008,
"max": 0.5813750999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.605932333333341e-05,
"min": 6.605932333333341e-05,
"max": 0.004922643772500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019817797000000023,
"min": 0.00019817797000000023,
"max": 0.014070617489999998,
"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": "1729756360",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"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": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729758870"
},
"total": 2510.274570732,
"count": 1,
"self": 0.4357261590002963,
"children": {
"run_training.setup": {
"total": 0.07945160899998882,
"count": 1,
"self": 0.07945160899998882
},
"TrainerController.start_learning": {
"total": 2509.7593929639997,
"count": 1,
"self": 4.58033023006783,
"children": {
"TrainerController._reset_env": {
"total": 4.825497091999978,
"count": 1,
"self": 4.825497091999978
},
"TrainerController.advance": {
"total": 2500.2412041279317,
"count": 231882,
"self": 4.637539187802304,
"children": {
"env_step": {
"total": 1978.1284254680713,
"count": 231882,
"self": 1556.295620635099,
"children": {
"SubprocessEnvManager._take_step": {
"total": 418.96523536104627,
"count": 231882,
"self": 15.850321019020498,
"children": {
"TorchPolicy.evaluate": {
"total": 403.11491434202577,
"count": 223146,
"self": 403.11491434202577
}
}
},
"workers": {
"total": 2.8675694719260036,
"count": 231882,
"self": 0.0,
"children": {
"worker_root": {
"total": 2502.432062752947,
"count": 231882,
"is_parallel": true,
"self": 1239.3475513339158,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007859739999958038,
"count": 1,
"is_parallel": true,
"self": 0.00023290100000394887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005530729999918549,
"count": 2,
"is_parallel": true,
"self": 0.0005530729999918549
}
}
},
"UnityEnvironment.step": {
"total": 0.028750019000028715,
"count": 1,
"is_parallel": true,
"self": 0.00040950200008182946,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019705400001157614,
"count": 1,
"is_parallel": true,
"self": 0.00019705400001157614
},
"communicator.exchange": {
"total": 0.027387197999985347,
"count": 1,
"is_parallel": true,
"self": 0.027387197999985347
},
"steps_from_proto": {
"total": 0.0007562649999499627,
"count": 1,
"is_parallel": true,
"self": 0.0002323289999139888,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005239360000359738,
"count": 2,
"is_parallel": true,
"self": 0.0005239360000359738
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1263.084511419031,
"count": 231881,
"is_parallel": true,
"self": 37.41577717026644,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.9238980819652,
"count": 231881,
"is_parallel": true,
"self": 83.9238980819652
},
"communicator.exchange": {
"total": 1051.7797548418648,
"count": 231881,
"is_parallel": true,
"self": 1051.7797548418648
},
"steps_from_proto": {
"total": 89.96508132493454,
"count": 231881,
"is_parallel": true,
"self": 34.23514364184274,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.729937683091805,
"count": 463762,
"is_parallel": true,
"self": 55.729937683091805
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.4752394720581,
"count": 231882,
"self": 6.662549029994182,
"children": {
"process_trajectory": {
"total": 169.70022096606323,
"count": 231882,
"self": 168.45084542406363,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2493755419995978,
"count": 10,
"self": 1.2493755419995978
}
}
},
"_update_policy": {
"total": 341.1124694760007,
"count": 97,
"self": 274.9378027530073,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.17466672299338,
"count": 2910,
"self": 66.17466672299338
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0290000318491366e-06,
"count": 1,
"self": 1.0290000318491366e-06
},
"TrainerController._save_models": {
"total": 0.11236048499995377,
"count": 1,
"self": 0.002661849000105576,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10969863599984819,
"count": 1,
"self": 0.10969863599984819
}
}
}
}
}
}
}