ppo-Huggy / run_logs /timers.json
Gyaneshere's picture
Huggy
6feef9f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.409183382987976,
"min": 1.409183382987976,
"max": 1.429460048675537,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70129.421875,
"min": 69772.75,
"max": 75861.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.70884146341463,
"min": 70.24285714285715,
"max": 418.9166666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49665.0,
"min": 49117.0,
"max": 50270.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999562.0,
"min": 49768.0,
"max": 1999562.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999562.0,
"min": 49768.0,
"max": 1999562.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.461406707763672,
"min": 0.09398988634347916,
"max": 2.533802032470703,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1612.221435546875,
"min": 11.184796333312988,
"max": 1736.67431640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8075953263362856,
"min": 1.7990913427427035,
"max": 4.017473471295498,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2493.974938750267,
"min": 214.09186978638172,
"max": 2711.8336150050163,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8075953263362856,
"min": 1.7990913427427035,
"max": 4.017473471295498,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2493.974938750267,
"min": 214.09186978638172,
"max": 2711.8336150050163,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015930431098483192,
"min": 0.01396494792861631,
"max": 0.021182094870891885,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04779129329544958,
"min": 0.02792989585723262,
"max": 0.058304695420277615,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.061044180517395345,
"min": 0.021853677555918695,
"max": 0.06186752344171206,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18313254155218603,
"min": 0.04370735511183739,
"max": 0.18468924127519132,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.007948664050002e-06,
"min": 4.007948664050002e-06,
"max": 0.000295311376562875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2023845992150004e-05,
"min": 1.2023845992150004e-05,
"max": 0.0008441421186192999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10133594999999997,
"min": 0.10133594999999997,
"max": 0.19843712500000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3040078499999999,
"min": 0.20784529999999996,
"max": 0.5813807000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.666390500000002e-05,
"min": 7.666390500000002e-05,
"max": 0.004922012537499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022999171500000007,
"min": 0.00022999171500000007,
"max": 0.014070896930000003,
"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": "1739215345",
"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": "1739217853"
},
"total": 2507.5395324260003,
"count": 1,
"self": 0.4411670990002676,
"children": {
"run_training.setup": {
"total": 0.023664203000066664,
"count": 1,
"self": 0.023664203000066664
},
"TrainerController.start_learning": {
"total": 2507.074701124,
"count": 1,
"self": 4.583330425944496,
"children": {
"TrainerController._reset_env": {
"total": 3.0171117700000423,
"count": 1,
"self": 3.0171117700000423
},
"TrainerController.advance": {
"total": 2499.3611147400557,
"count": 233293,
"self": 4.8797352191827486,
"children": {
"env_step": {
"total": 1980.0931918759688,
"count": 233293,
"self": 1551.0851141829858,
"children": {
"SubprocessEnvManager._take_step": {
"total": 426.26392932492536,
"count": 233293,
"self": 15.889107938873735,
"children": {
"TorchPolicy.evaluate": {
"total": 410.3748213860516,
"count": 222908,
"self": 410.3748213860516
}
}
},
"workers": {
"total": 2.744148368057836,
"count": 233293,
"self": 0.0,
"children": {
"worker_root": {
"total": 2499.384895407964,
"count": 233293,
"is_parallel": true,
"self": 1238.6992033579895,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009998939999604772,
"count": 1,
"is_parallel": true,
"self": 0.0003482639999674575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006516299999930197,
"count": 2,
"is_parallel": true,
"self": 0.0006516299999930197
}
}
},
"UnityEnvironment.step": {
"total": 0.0294158530000459,
"count": 1,
"is_parallel": true,
"self": 0.0003134190000082526,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022564200003216683,
"count": 1,
"is_parallel": true,
"self": 0.00022564200003216683
},
"communicator.exchange": {
"total": 0.02817897600004926,
"count": 1,
"is_parallel": true,
"self": 0.02817897600004926
},
"steps_from_proto": {
"total": 0.0006978159999562195,
"count": 1,
"is_parallel": true,
"self": 0.00020191699991300993,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004958990000432095,
"count": 2,
"is_parallel": true,
"self": 0.0004958990000432095
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.6856920499745,
"count": 233292,
"is_parallel": true,
"self": 37.5812812499953,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.4767215930234,
"count": 233292,
"is_parallel": true,
"self": 81.4767215930234
},
"communicator.exchange": {
"total": 1053.0655225509195,
"count": 233292,
"is_parallel": true,
"self": 1053.0655225509195
},
"steps_from_proto": {
"total": 88.56216665603642,
"count": 233292,
"is_parallel": true,
"self": 32.85829315510705,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.703873500929376,
"count": 466584,
"is_parallel": true,
"self": 55.703873500929376
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 514.3881876449038,
"count": 233293,
"self": 6.750763036841477,
"children": {
"process_trajectory": {
"total": 173.07368905405872,
"count": 233293,
"self": 171.75065913305832,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3230299210003977,
"count": 10,
"self": 1.3230299210003977
}
}
},
"_update_policy": {
"total": 334.56373555400364,
"count": 97,
"self": 267.2853893109932,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.27834624301045,
"count": 2910,
"self": 67.27834624301045
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.899998308857903e-07,
"count": 1,
"self": 7.899998308857903e-07
},
"TrainerController._save_models": {
"total": 0.11314339799992013,
"count": 1,
"self": 0.001870353999947838,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11127304399997229,
"count": 1,
"self": 0.11127304399997229
}
}
}
}
}
}
}