ppo-Huggy / run_logs /timers.json
pedroroblesduten's picture
Huggy
61c67c0
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407181978225708,
"min": 1.407181978225708,
"max": 1.426453948020935,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71556.609375,
"min": 68797.15625,
"max": 77064.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.0190114068441,
"min": 88.05704099821747,
"max": 373.44029850746267,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49454.0,
"min": 48916.0,
"max": 50174.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49771.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49771.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.343769073486328,
"min": 0.08182468265295029,
"max": 2.3920164108276367,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1232.822509765625,
"min": 10.882682800292969,
"max": 1306.33154296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6414867395910475,
"min": 1.7437462999408406,
"max": 3.9486104281160843,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1915.422025024891,
"min": 231.9182578921318,
"max": 2088.6565989255905,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6414867395910475,
"min": 1.7437462999408406,
"max": 3.9486104281160843,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1915.422025024891,
"min": 231.9182578921318,
"max": 2088.6565989255905,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01745012671001152,
"min": 0.013753407106075127,
"max": 0.020435369992204265,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05235038013003457,
"min": 0.027506814212150253,
"max": 0.05767494727139516,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05254495528837045,
"min": 0.02125070079540213,
"max": 0.06081981919705868,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15763486586511136,
"min": 0.04250140159080426,
"max": 0.16594424781699973,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2589489137166798e-06,
"min": 3.2589489137166798e-06,
"max": 0.00029533695155435,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.77684674115004e-06,
"min": 9.77684674115004e-06,
"max": 0.0008442624185791998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108628333333332,
"min": 0.10108628333333332,
"max": 0.19844565000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30325884999999997,
"min": 0.20733990000000002,
"max": 0.5814208000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.420553833333356e-05,
"min": 6.420553833333356e-05,
"max": 0.004922437934999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019261661500000066,
"min": 0.00019261661500000066,
"max": 0.01407289792,
"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": "1690748450",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1690751230"
},
"total": 2779.237709179,
"count": 1,
"self": 0.43843455400019593,
"children": {
"run_training.setup": {
"total": 0.038027814999963994,
"count": 1,
"self": 0.038027814999963994
},
"TrainerController.start_learning": {
"total": 2778.7612468099996,
"count": 1,
"self": 5.025212360059413,
"children": {
"TrainerController._reset_env": {
"total": 5.90510919999997,
"count": 1,
"self": 5.90510919999997
},
"TrainerController.advance": {
"total": 2767.7010217099405,
"count": 232086,
"self": 5.111278253904402,
"children": {
"env_step": {
"total": 2147.2366691990273,
"count": 232086,
"self": 1815.2972725000523,
"children": {
"SubprocessEnvManager._take_step": {
"total": 328.5923533169765,
"count": 232086,
"self": 18.722723299961103,
"children": {
"TorchPolicy.evaluate": {
"total": 309.8696300170154,
"count": 223056,
"self": 309.8696300170154
}
}
},
"workers": {
"total": 3.34704338199856,
"count": 232086,
"self": 0.0,
"children": {
"worker_root": {
"total": 2770.098425632018,
"count": 232086,
"is_parallel": true,
"self": 1286.8943188501116,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010137659999145399,
"count": 1,
"is_parallel": true,
"self": 0.000298642999950971,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007151229999635689,
"count": 2,
"is_parallel": true,
"self": 0.0007151229999635689
}
}
},
"UnityEnvironment.step": {
"total": 0.0352006219999339,
"count": 1,
"is_parallel": true,
"self": 0.00037409699996260315,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002565939998930844,
"count": 1,
"is_parallel": true,
"self": 0.0002565939998930844
},
"communicator.exchange": {
"total": 0.033670536000045104,
"count": 1,
"is_parallel": true,
"self": 0.033670536000045104
},
"steps_from_proto": {
"total": 0.0008993950000331097,
"count": 1,
"is_parallel": true,
"self": 0.0002697620000162715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006296330000168382,
"count": 2,
"is_parallel": true,
"self": 0.0006296330000168382
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1483.2041067819064,
"count": 232085,
"is_parallel": true,
"self": 44.50766879480898,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 95.95596626403619,
"count": 232085,
"is_parallel": true,
"self": 95.95596626403619
},
"communicator.exchange": {
"total": 1234.2558919529893,
"count": 232085,
"is_parallel": true,
"self": 1234.2558919529893
},
"steps_from_proto": {
"total": 108.48457977007183,
"count": 232085,
"is_parallel": true,
"self": 41.930371125129454,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.55420864494238,
"count": 464170,
"is_parallel": true,
"self": 66.55420864494238
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 615.3530742570086,
"count": 232086,
"self": 7.450136344076668,
"children": {
"process_trajectory": {
"total": 152.26376958193248,
"count": 232086,
"self": 150.8024308509324,
"children": {
"RLTrainer._checkpoint": {
"total": 1.461338731000069,
"count": 10,
"self": 1.461338731000069
}
}
},
"_update_policy": {
"total": 455.6391683309995,
"count": 97,
"self": 391.9466706740054,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.69249765699408,
"count": 2910,
"self": 63.69249765699408
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.66999778029276e-07,
"count": 1,
"self": 9.66999778029276e-07
},
"TrainerController._save_models": {
"total": 0.1299025729999812,
"count": 1,
"self": 0.0020534229997792863,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12784915000020192,
"count": 1,
"self": 0.12784915000020192
}
}
}
}
}
}
}