ppo-Huggy / run_logs /timers.json
reddest-panda's picture
Huggy
e4e5ce7 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4072351455688477,
"min": 1.4072351455688477,
"max": 1.425726056098938,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69995.875,
"min": 68877.2265625,
"max": 75199.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 67.559670781893,
"min": 65.9611780455154,
"max": 388.3333333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49251.0,
"min": 49200.0,
"max": 50095.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999923.0,
"min": 49516.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999923.0,
"min": 49516.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5453243255615234,
"min": -0.0025602267123758793,
"max": 2.5453243255615234,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1855.54150390625,
"min": -0.32770901918411255,
"max": 1883.0211181640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9971471885104237,
"min": 1.717848385218531,
"max": 4.077331420867034,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2913.920300424099,
"min": 219.88459330797195,
"max": 2943.6558830738068,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9971471885104237,
"min": 1.717848385218531,
"max": 4.077331420867034,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2913.920300424099,
"min": 219.88459330797195,
"max": 2943.6558830738068,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01659915917455995,
"min": 0.014770803425926715,
"max": 0.02001783598267745,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04979747752367984,
"min": 0.02961164564573361,
"max": 0.05949566712855206,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05879671424627305,
"min": 0.023732562735676765,
"max": 0.0647342858215173,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17639014273881914,
"min": 0.04746512547135353,
"max": 0.19169839173555375,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.909698696799992e-06,
"min": 3.909698696799992e-06,
"max": 0.00029533035155654994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1729096090399974e-05,
"min": 1.1729096090399974e-05,
"max": 0.0008439336186887999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1013032,
"min": 0.1013032,
"max": 0.19844345000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039096,
"min": 0.20773975,
"max": 0.5813112,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.502967999999987e-05,
"min": 7.502967999999987e-05,
"max": 0.004922328155000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022508903999999964,
"min": 0.00022508903999999964,
"max": 0.01406742888,
"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": "1722009406",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722011787"
},
"total": 2381.280212952,
"count": 1,
"self": 0.8534541310004897,
"children": {
"run_training.setup": {
"total": 0.06119507500000054,
"count": 1,
"self": 0.06119507500000054
},
"TrainerController.start_learning": {
"total": 2380.3655637459997,
"count": 1,
"self": 4.249675366005249,
"children": {
"TrainerController._reset_env": {
"total": 2.9342072470000176,
"count": 1,
"self": 2.9342072470000176
},
"TrainerController.advance": {
"total": 2372.9882302359947,
"count": 233808,
"self": 4.716058459029227,
"children": {
"env_step": {
"total": 1866.785342882079,
"count": 233808,
"self": 1541.647187321118,
"children": {
"SubprocessEnvManager._take_step": {
"total": 322.339717922971,
"count": 233808,
"self": 16.09109426587304,
"children": {
"TorchPolicy.evaluate": {
"total": 306.24862365709794,
"count": 222882,
"self": 306.24862365709794
}
}
},
"workers": {
"total": 2.7984376379899913,
"count": 233808,
"self": 0.0,
"children": {
"worker_root": {
"total": 2372.6941864740515,
"count": 233808,
"is_parallel": true,
"self": 1130.3298935131666,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000895930999945449,
"count": 1,
"is_parallel": true,
"self": 0.0002441689999841401,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006517619999613089,
"count": 2,
"is_parallel": true,
"self": 0.0006517619999613089
}
}
},
"UnityEnvironment.step": {
"total": 0.030015515000059168,
"count": 1,
"is_parallel": true,
"self": 0.00038608700003806007,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001921599999832324,
"count": 1,
"is_parallel": true,
"self": 0.0001921599999832324
},
"communicator.exchange": {
"total": 0.02869636499997341,
"count": 1,
"is_parallel": true,
"self": 0.02869636499997341
},
"steps_from_proto": {
"total": 0.0007409030000644634,
"count": 1,
"is_parallel": true,
"self": 0.00018965100014156633,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005512519999228971,
"count": 2,
"is_parallel": true,
"self": 0.0005512519999228971
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1242.364292960885,
"count": 233807,
"is_parallel": true,
"self": 38.68930500879742,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.96324939004535,
"count": 233807,
"is_parallel": true,
"self": 79.96324939004535
},
"communicator.exchange": {
"total": 1034.9128043439975,
"count": 233807,
"is_parallel": true,
"self": 1034.9128043439975
},
"steps_from_proto": {
"total": 88.79893421804479,
"count": 233807,
"is_parallel": true,
"self": 31.790138360023207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.008795858021585,
"count": 467614,
"is_parallel": true,
"self": 57.008795858021585
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 501.48682889488646,
"count": 233808,
"self": 6.604656386881402,
"children": {
"process_trajectory": {
"total": 161.02877382300358,
"count": 233808,
"self": 159.68746513900282,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3413086840007509,
"count": 10,
"self": 1.3413086840007509
}
}
},
"_update_policy": {
"total": 333.8533986850015,
"count": 97,
"self": 270.17721562400993,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.67618306099155,
"count": 2910,
"self": 63.67618306099155
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4289998944150284e-06,
"count": 1,
"self": 1.4289998944150284e-06
},
"TrainerController._save_models": {
"total": 0.19344946799992613,
"count": 1,
"self": 0.00305482200019469,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19039464599973144,
"count": 1,
"self": 0.19039464599973144
}
}
}
}
}
}
}