ppo-Huggy / run_logs /timers.json
Akchunks's picture
Huggy
ea55539 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4032763242721558,
"min": 1.4032654762268066,
"max": 1.427049160003662,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70549.71875,
"min": 68586.7265625,
"max": 76341.390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.30737704918033,
"min": 86.4676007005254,
"max": 397.1732283464567,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49438.0,
"min": 49092.0,
"max": 50441.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999890.0,
"min": 49847.0,
"max": 1999890.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999890.0,
"min": 49847.0,
"max": 1999890.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3630964756011963,
"min": 0.07912862300872803,
"max": 2.4316494464874268,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1153.1910400390625,
"min": 9.970206260681152,
"max": 1367.956787109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6696596560908143,
"min": 1.8534972767035167,
"max": 3.9979207555003984,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1790.7939121723175,
"min": 233.5406568646431,
"max": 2147.2611285448074,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6696596560908143,
"min": 1.8534972767035167,
"max": 3.9979207555003984,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1790.7939121723175,
"min": 233.5406568646431,
"max": 2147.2611285448074,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017837462727847097,
"min": 0.014146949659334496,
"max": 0.019579307948394367,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05351238818354129,
"min": 0.02829389931866899,
"max": 0.05450483273307327,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.044336210356818305,
"min": 0.021990168715516727,
"max": 0.05910656669487556,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1330086310704549,
"min": 0.04398033743103345,
"max": 0.17193863019347191,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.447348850916668e-06,
"min": 3.447348850916668e-06,
"max": 0.0002953185015605,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0342046552750004e-05,
"min": 1.0342046552750004e-05,
"max": 0.0008440521186492999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114908333333332,
"min": 0.10114908333333332,
"max": 0.19843950000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30344724999999995,
"min": 0.20745745000000004,
"max": 0.5813507000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.733925833333338e-05,
"min": 6.733925833333338e-05,
"max": 0.00492213105,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020201777500000013,
"min": 0.00020201777500000013,
"max": 0.01406939993,
"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": "1748234199",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748236696"
},
"total": 2497.770432564,
"count": 1,
"self": 0.437933551000242,
"children": {
"run_training.setup": {
"total": 0.02559887199993227,
"count": 1,
"self": 0.02559887199993227
},
"TrainerController.start_learning": {
"total": 2497.306900141,
"count": 1,
"self": 4.329162188988448,
"children": {
"TrainerController._reset_env": {
"total": 3.138144902000022,
"count": 1,
"self": 3.138144902000022
},
"TrainerController.advance": {
"total": 2489.714015019011,
"count": 232132,
"self": 4.7761544300897185,
"children": {
"env_step": {
"total": 1967.9489028039504,
"count": 232132,
"self": 1546.2340078519383,
"children": {
"SubprocessEnvManager._take_step": {
"total": 419.0243440899917,
"count": 232132,
"self": 16.137468670932662,
"children": {
"TorchPolicy.evaluate": {
"total": 402.88687541905904,
"count": 223037,
"self": 402.88687541905904
}
}
},
"workers": {
"total": 2.6905508620204728,
"count": 232132,
"self": 0.0,
"children": {
"worker_root": {
"total": 2489.9180441039607,
"count": 232132,
"is_parallel": true,
"self": 1229.0779584558923,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000916327000027195,
"count": 1,
"is_parallel": true,
"self": 0.00030533799997556343,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006109890000516316,
"count": 2,
"is_parallel": true,
"self": 0.0006109890000516316
}
}
},
"UnityEnvironment.step": {
"total": 0.02978663300007156,
"count": 1,
"is_parallel": true,
"self": 0.0003057660001104523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018592300000364048,
"count": 1,
"is_parallel": true,
"self": 0.00018592300000364048
},
"communicator.exchange": {
"total": 0.028604250999933356,
"count": 1,
"is_parallel": true,
"self": 0.028604250999933356
},
"steps_from_proto": {
"total": 0.0006906930000241118,
"count": 1,
"is_parallel": true,
"self": 0.00019026400013899547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005004289998851164,
"count": 2,
"is_parallel": true,
"self": 0.0005004289998851164
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.8400856480685,
"count": 232131,
"is_parallel": true,
"self": 37.34378082212925,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.32517787406607,
"count": 232131,
"is_parallel": true,
"self": 83.32517787406607
},
"communicator.exchange": {
"total": 1051.4510790289346,
"count": 232131,
"is_parallel": true,
"self": 1051.4510790289346
},
"steps_from_proto": {
"total": 88.72004792293853,
"count": 232131,
"is_parallel": true,
"self": 33.14834509688262,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.57170282605591,
"count": 464262,
"is_parallel": true,
"self": 55.57170282605591
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 516.9889577849709,
"count": 232132,
"self": 6.859154479951712,
"children": {
"process_trajectory": {
"total": 162.32213065601832,
"count": 232132,
"self": 160.82744606901838,
"children": {
"RLTrainer._checkpoint": {
"total": 1.494684586999938,
"count": 10,
"self": 1.494684586999938
}
}
},
"_update_policy": {
"total": 347.8076726490009,
"count": 97,
"self": 279.79353088400126,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.01414176499964,
"count": 2910,
"self": 68.01414176499964
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.450000106880907e-07,
"count": 1,
"self": 9.450000106880907e-07
},
"TrainerController._save_models": {
"total": 0.12557708600024853,
"count": 1,
"self": 0.001552696000544529,
"children": {
"RLTrainer._checkpoint": {
"total": 0.124024389999704,
"count": 1,
"self": 0.124024389999704
}
}
}
}
}
}
}