ppo-Huggy / run_logs /timers.json
miki5799's picture
Huggy
e156544 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045965671539307,
"min": 1.4045965671539307,
"max": 1.4286978244781494,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69076.65625,
"min": 68341.2265625,
"max": 76777.5625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.58986928104575,
"min": 80.58986928104575,
"max": 391.2325581395349,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49321.0,
"min": 48819.0,
"max": 50469.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999949.0,
"min": 49977.0,
"max": 1999949.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999949.0,
"min": 49977.0,
"max": 1999949.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4339730739593506,
"min": 0.11136406660079956,
"max": 2.4760992527008057,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1489.591552734375,
"min": 14.254600524902344,
"max": 1489.591552734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7653578852905945,
"min": 1.8374028569087386,
"max": 3.9231319003303846,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2304.399025797844,
"min": 235.18756568431854,
"max": 2353.8791401982307,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7653578852905945,
"min": 1.8374028569087386,
"max": 3.9231319003303846,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2304.399025797844,
"min": 235.18756568431854,
"max": 2353.8791401982307,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01844812749445231,
"min": 0.013648660851201082,
"max": 0.020115048826361698,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.055344382483356935,
"min": 0.027297321702402164,
"max": 0.06015072577962807,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.061372966981596416,
"min": 0.022107777154694003,
"max": 0.061372966981596416,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18411890094478925,
"min": 0.044215554309388005,
"max": 0.18411890094478925,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3547488817833365e-06,
"min": 3.3547488817833365e-06,
"max": 0.00029535825154724995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.006424664535001e-05,
"min": 1.006424664535001e-05,
"max": 0.0008442078185974,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111821666666665,
"min": 0.10111821666666665,
"max": 0.19845275,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30335464999999995,
"min": 0.2074137,
"max": 0.5814026,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.579901166666674e-05,
"min": 6.579901166666674e-05,
"max": 0.004922792225000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019739703500000022,
"min": 0.00019739703500000022,
"max": 0.014071989739999995,
"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": "1730135587",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730138247"
},
"total": 2659.590218247,
"count": 1,
"self": 0.48817250299998705,
"children": {
"run_training.setup": {
"total": 0.055718898000009176,
"count": 1,
"self": 0.055718898000009176
},
"TrainerController.start_learning": {
"total": 2659.046326846,
"count": 1,
"self": 5.043719381962092,
"children": {
"TrainerController._reset_env": {
"total": 2.624067762999971,
"count": 1,
"self": 2.624067762999971
},
"TrainerController.advance": {
"total": 2651.263696285038,
"count": 232077,
"self": 5.2132955429519825,
"children": {
"env_step": {
"total": 2119.932858494946,
"count": 232077,
"self": 1666.9707913389616,
"children": {
"SubprocessEnvManager._take_step": {
"total": 449.8281596840317,
"count": 232077,
"self": 17.334784248002507,
"children": {
"TorchPolicy.evaluate": {
"total": 432.49337543602917,
"count": 222876,
"self": 432.49337543602917
}
}
},
"workers": {
"total": 3.1339074719525115,
"count": 232077,
"self": 0.0,
"children": {
"worker_root": {
"total": 2651.105490891932,
"count": 232077,
"is_parallel": true,
"self": 1305.8557328898542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009148120000190829,
"count": 1,
"is_parallel": true,
"self": 0.000261145000081342,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006536669999377409,
"count": 2,
"is_parallel": true,
"self": 0.0006536669999377409
}
}
},
"UnityEnvironment.step": {
"total": 0.04106259200000295,
"count": 1,
"is_parallel": true,
"self": 0.0003639199999270204,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019300600001770363,
"count": 1,
"is_parallel": true,
"self": 0.00019300600001770363
},
"communicator.exchange": {
"total": 0.03970383099999708,
"count": 1,
"is_parallel": true,
"self": 0.03970383099999708
},
"steps_from_proto": {
"total": 0.0008018350000611463,
"count": 1,
"is_parallel": true,
"self": 0.0002183010001317598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005835339999293865,
"count": 2,
"is_parallel": true,
"self": 0.0005835339999293865
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1345.2497580020777,
"count": 232076,
"is_parallel": true,
"self": 40.387914077960204,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.84512772904259,
"count": 232076,
"is_parallel": true,
"self": 86.84512772904259
},
"communicator.exchange": {
"total": 1121.3514883110538,
"count": 232076,
"is_parallel": true,
"self": 1121.3514883110538
},
"steps_from_proto": {
"total": 96.66522788402108,
"count": 232076,
"is_parallel": true,
"self": 36.537933065947755,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.127294818073324,
"count": 464152,
"is_parallel": true,
"self": 60.127294818073324
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 526.1175422471404,
"count": 232077,
"self": 7.493551120055486,
"children": {
"process_trajectory": {
"total": 170.379642799086,
"count": 232077,
"self": 168.79798161508586,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5816611840001542,
"count": 10,
"self": 1.5816611840001542
}
}
},
"_update_policy": {
"total": 348.24434832799886,
"count": 97,
"self": 279.9340319949829,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.31031633301598,
"count": 2910,
"self": 68.31031633301598
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.02400008472614e-06,
"count": 1,
"self": 1.02400008472614e-06
},
"TrainerController._save_models": {
"total": 0.11484239199990043,
"count": 1,
"self": 0.001921871999911673,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11292051999998876,
"count": 1,
"self": 0.11292051999998876
}
}
}
}
}
}
}