ppo-Huggy / run_logs /timers.json
SwordAndTea's picture
Huggy
d4a912d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4011204242706299,
"min": 1.4011204242706299,
"max": 1.42475426197052,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71352.0546875,
"min": 68794.546875,
"max": 77748.359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.63398692810458,
"min": 76.14285714285714,
"max": 403.508064516129,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49348.0,
"min": 49071.0,
"max": 50035.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49879.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49879.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5348076820373535,
"min": 0.02289951965212822,
"max": 2.5348076820373535,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1551.30224609375,
"min": 2.816640853881836,
"max": 1618.08447265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.963904799394358,
"min": 1.8503602893371893,
"max": 3.980530870026165,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2425.9097372293472,
"min": 227.59431558847427,
"max": 2530.9293941259384,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.963904799394358,
"min": 1.8503602893371893,
"max": 3.980530870026165,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2425.9097372293472,
"min": 227.59431558847427,
"max": 2530.9293941259384,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01735438543627323,
"min": 0.013745478159277506,
"max": 0.02027438136865385,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05206315630881969,
"min": 0.027490956318555013,
"max": 0.05932032210209097,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05911607291135523,
"min": 0.023097891050080456,
"max": 0.06131736480941376,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1773482187340657,
"min": 0.04619578210016091,
"max": 0.18090442990263303,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.820698726466662e-06,
"min": 3.820698726466662e-06,
"max": 0.00029537070154309997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1462096179399986e-05,
"min": 1.1462096179399986e-05,
"max": 0.0008444190185269999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127353333333333,
"min": 0.10127353333333333,
"max": 0.19845690000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038206,
"min": 0.20769525,
"max": 0.5814730000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.354931333333329e-05,
"min": 7.354931333333329e-05,
"max": 0.004922999310000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022064793999999988,
"min": 0.00022064793999999988,
"max": 0.014075502700000003,
"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": "1728693741",
"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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728696294"
},
"total": 2553.460240063,
"count": 1,
"self": 0.4407505260001017,
"children": {
"run_training.setup": {
"total": 0.0963230749999866,
"count": 1,
"self": 0.0963230749999866
},
"TrainerController.start_learning": {
"total": 2552.923166462,
"count": 1,
"self": 4.537709348899625,
"children": {
"TrainerController._reset_env": {
"total": 2.638894225999934,
"count": 1,
"self": 2.638894225999934
},
"TrainerController.advance": {
"total": 2545.6305684671006,
"count": 232632,
"self": 4.688656683083991,
"children": {
"env_step": {
"total": 2012.5427447630423,
"count": 232632,
"self": 1595.8984136480399,
"children": {
"SubprocessEnvManager._take_step": {
"total": 413.78276408396243,
"count": 232632,
"self": 15.964304380910221,
"children": {
"TorchPolicy.evaluate": {
"total": 397.8184597030522,
"count": 222966,
"self": 397.8184597030522
}
}
},
"workers": {
"total": 2.86156703103984,
"count": 232632,
"self": 0.0,
"children": {
"worker_root": {
"total": 2545.776843011212,
"count": 232632,
"is_parallel": true,
"self": 1253.0325321082435,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009120849999817437,
"count": 1,
"is_parallel": true,
"self": 0.00024222299998655217,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006698619999951916,
"count": 2,
"is_parallel": true,
"self": 0.0006698619999951916
}
}
},
"UnityEnvironment.step": {
"total": 0.030421547999935683,
"count": 1,
"is_parallel": true,
"self": 0.0004142029999911756,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019329600002038205,
"count": 1,
"is_parallel": true,
"self": 0.00019329600002038205
},
"communicator.exchange": {
"total": 0.028986790999965706,
"count": 1,
"is_parallel": true,
"self": 0.028986790999965706
},
"steps_from_proto": {
"total": 0.0008272579999584195,
"count": 1,
"is_parallel": true,
"self": 0.00022667999996883736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006005779999895822,
"count": 2,
"is_parallel": true,
"self": 0.0006005779999895822
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1292.7443109029684,
"count": 232631,
"is_parallel": true,
"self": 39.20036230481264,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.15680809011542,
"count": 232631,
"is_parallel": true,
"self": 81.15680809011542
},
"communicator.exchange": {
"total": 1080.6358180069878,
"count": 232631,
"is_parallel": true,
"self": 1080.6358180069878
},
"steps_from_proto": {
"total": 91.75132250105253,
"count": 232631,
"is_parallel": true,
"self": 32.38043735604924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.370885145003285,
"count": 465262,
"is_parallel": true,
"self": 59.370885145003285
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 528.3991670209742,
"count": 232632,
"self": 7.050098131958862,
"children": {
"process_trajectory": {
"total": 172.64688341301655,
"count": 232632,
"self": 171.26617233501622,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3807110780003313,
"count": 10,
"self": 1.3807110780003313
}
}
},
"_update_policy": {
"total": 348.7021854759988,
"count": 97,
"self": 279.52174447399636,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.18044100200245,
"count": 2910,
"self": 69.18044100200245
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.78999651124468e-07,
"count": 1,
"self": 9.78999651124468e-07
},
"TrainerController._save_models": {
"total": 0.1159934410002279,
"count": 1,
"self": 0.0019181070001650369,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11407533400006287,
"count": 1,
"self": 0.11407533400006287
}
}
}
}
}
}
}