ppo-Huggy / run_logs /timers.json
veverara's picture
Huggy
fe279e6 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405712366104126,
"min": 1.405712366104126,
"max": 1.427901268005371,
"count": 29
},
"Huggy.Policy.Entropy.sum": {
"value": 69183.5390625,
"min": 68130.7578125,
"max": 76183.0703125,
"count": 29
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.71830985915493,
"min": 91.5,
"max": 413.198347107438,
"count": 29
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49560.0,
"min": 49044.0,
"max": 49997.0,
"count": 29
},
"Huggy.Step.mean": {
"value": 1449989.0,
"min": 49388.0,
"max": 1449989.0,
"count": 29
},
"Huggy.Step.sum": {
"value": 1449989.0,
"min": 49388.0,
"max": 1449989.0,
"count": 29
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.367757797241211,
"min": 0.09309158474206924,
"max": 2.385925054550171,
"count": 29
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1176.775634765625,
"min": 11.170989990234375,
"max": 1260.2418212890625,
"count": 29
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.718104224449672,
"min": 1.7763444552818934,
"max": 3.849414949108954,
"count": 29
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1847.897799551487,
"min": 213.1613346338272,
"max": 1995.444445848465,
"count": 29
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.718104224449672,
"min": 1.7763444552818934,
"max": 3.849414949108954,
"count": 29
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1847.897799551487,
"min": 213.1613346338272,
"max": 1995.444445848465,
"count": 29
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014657947997410601,
"min": 0.014329018285692049,
"max": 0.021316938515519725,
"count": 29
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0439738439922318,
"min": 0.028658036571384098,
"max": 0.05413878678421801,
"count": 29
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05631038778358036,
"min": 0.021891366690397263,
"max": 0.05710392602615886,
"count": 29
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16893116335074107,
"min": 0.043782733380794525,
"max": 0.17131177807847658,
"count": 29
},
"Huggy.Policy.LearningRate.mean": {
"value": 8.645477118176668e-05,
"min": 8.645477118176668e-05,
"max": 0.00029535652654782496,
"count": 29
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.0002593643135453,
"min": 0.00018841483719510003,
"max": 0.0008441541186152998,
"count": 29
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.12881823333333334,
"min": 0.12881823333333334,
"max": 0.19845217499999998,
"count": 29
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.38645470000000004,
"min": 0.2628049,
"max": 0.5813847,
"count": 29
},
"Huggy.Policy.Beta.mean": {
"value": 0.0014480298433333335,
"min": 0.0014480298433333335,
"max": 0.004922763532499999,
"count": 29
},
"Huggy.Policy.Beta.sum": {
"value": 0.00434408953,
"min": 0.003153964510000001,
"max": 0.014071096529999997,
"count": 29
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 29
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 29
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740496580",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740498328"
},
"total": 1747.545996925,
"count": 1,
"self": 0.44092490500020176,
"children": {
"run_training.setup": {
"total": 0.02939599299998008,
"count": 1,
"self": 0.02939599299998008
},
"TrainerController.start_learning": {
"total": 1747.0756760269999,
"count": 1,
"self": 3.09717930404895,
"children": {
"TrainerController._reset_env": {
"total": 2.992211555999802,
"count": 1,
"self": 2.992211555999802
},
"TrainerController.advance": {
"total": 1740.9859270849513,
"count": 170104,
"self": 3.2265641899996353,
"children": {
"env_step": {
"total": 1385.5952023109487,
"count": 170104,
"self": 1080.4050997938577,
"children": {
"SubprocessEnvManager._take_step": {
"total": 303.3856281070957,
"count": 170104,
"self": 11.200645553182994,
"children": {
"TorchPolicy.evaluate": {
"total": 292.18498255391273,
"count": 164074,
"self": 292.18498255391273
}
}
},
"workers": {
"total": 1.8044744099952368,
"count": 170103,
"self": 0.0,
"children": {
"worker_root": {
"total": 1741.769211878945,
"count": 170103,
"is_parallel": true,
"self": 858.047397441904,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010593500001050415,
"count": 1,
"is_parallel": true,
"self": 0.0003704950001974794,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006888549999075622,
"count": 2,
"is_parallel": true,
"self": 0.0006888549999075622
}
}
},
"UnityEnvironment.step": {
"total": 0.029539394000039465,
"count": 1,
"is_parallel": true,
"self": 0.0002998940003635653,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018469499991624616,
"count": 1,
"is_parallel": true,
"self": 0.00018469499991624616
},
"communicator.exchange": {
"total": 0.028347997999844665,
"count": 1,
"is_parallel": true,
"self": 0.028347997999844665
},
"steps_from_proto": {
"total": 0.0007068069999149884,
"count": 1,
"is_parallel": true,
"self": 0.00020848200006184925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004983249998531392,
"count": 2,
"is_parallel": true,
"self": 0.0004983249998531392
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 883.7218144370411,
"count": 170102,
"is_parallel": true,
"self": 27.35817359505654,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 59.451663668992296,
"count": 170102,
"is_parallel": true,
"self": 59.451663668992296
},
"communicator.exchange": {
"total": 732.7275277459903,
"count": 170102,
"is_parallel": true,
"self": 732.7275277459903
},
"steps_from_proto": {
"total": 64.18444942700194,
"count": 170102,
"is_parallel": true,
"self": 23.82005047706207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.36439894993987,
"count": 340204,
"is_parallel": true,
"self": 40.36439894993987
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 352.16416058400296,
"count": 170103,
"self": 4.5084612670193565,
"children": {
"process_trajectory": {
"total": 105.61277641298511,
"count": 170103,
"self": 104.75402457798464,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8587518350004757,
"count": 7,
"self": 0.8587518350004757
}
}
},
"_update_policy": {
"total": 242.0429229039985,
"count": 71,
"self": 193.70811527700153,
"children": {
"TorchPPOOptimizer.update": {
"total": 48.33480762699696,
"count": 2130,
"self": 48.33480762699696
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1449997145973612e-06,
"count": 1,
"self": 1.1449997145973612e-06
},
"TrainerController._save_models": {
"total": 0.0003569370001059724,
"count": 1,
"self": 3.201499976057676e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.00032492200034539565,
"count": 1,
"self": 0.00032492200034539565
}
}
}
}
}
}
}