ppo-Huggy / run_logs /timers.json
mikerocke's picture
Huggy
74e5591 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4074816703796387,
"min": 1.4074816703796387,
"max": 1.4322993755340576,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68385.3125,
"min": 68385.3125,
"max": 74963.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.3076923076923,
"min": 79.59838709677419,
"max": 406.9593495934959,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49560.0,
"min": 49000.0,
"max": 50056.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999961.0,
"min": 49933.0,
"max": 1999961.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999961.0,
"min": 49933.0,
"max": 1999961.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.434831380844116,
"min": 0.00028784474125131965,
"max": 2.4562010765075684,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1266.1123046875,
"min": 0.03511705994606018,
"max": 1490.6572265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6951972763125713,
"min": 1.7439415489063887,
"max": 3.9716902522976443,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1921.502583682537,
"min": 212.76086896657944,
"max": 2371.473294019699,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6951972763125713,
"min": 1.7439415489063887,
"max": 3.9716902522976443,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1921.502583682537,
"min": 212.76086896657944,
"max": 2371.473294019699,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015254092188034621,
"min": 0.013820757849498478,
"max": 0.019577174080445226,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045762276564103865,
"min": 0.027641515698996956,
"max": 0.058731522241335675,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054486776350273027,
"min": 0.021176452406992514,
"max": 0.061551373824477194,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1634603290508191,
"min": 0.04235290481398503,
"max": 0.17867749047776063,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5102988299333418e-06,
"min": 3.5102988299333418e-06,
"max": 0.0002953292265569249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0530896489800026e-05,
"min": 1.0530896489800026e-05,
"max": 0.0008441484186171998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117006666666668,
"min": 0.10117006666666668,
"max": 0.19844307500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30351020000000006,
"min": 0.20747335000000006,
"max": 0.5813828,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.83863266666668e-05,
"min": 6.83863266666668e-05,
"max": 0.004922309442500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020515898000000038,
"min": 0.00020515898000000038,
"max": 0.014071001719999997,
"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": "1724964123",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724966604"
},
"total": 2480.5207002029997,
"count": 1,
"self": 0.4256766009993953,
"children": {
"run_training.setup": {
"total": 0.05185070799996083,
"count": 1,
"self": 0.05185070799996083
},
"TrainerController.start_learning": {
"total": 2480.0431728940002,
"count": 1,
"self": 4.83690253998293,
"children": {
"TrainerController._reset_env": {
"total": 2.3458220310000115,
"count": 1,
"self": 2.3458220310000115
},
"TrainerController.advance": {
"total": 2472.742013429018,
"count": 232033,
"self": 4.807695819971286,
"children": {
"env_step": {
"total": 1957.266918931003,
"count": 232033,
"self": 1613.7128608501205,
"children": {
"SubprocessEnvManager._take_step": {
"total": 340.56187263998305,
"count": 232033,
"self": 16.261842899990995,
"children": {
"TorchPolicy.evaluate": {
"total": 324.30002973999206,
"count": 222904,
"self": 324.30002973999206
}
}
},
"workers": {
"total": 2.9921854408994477,
"count": 232033,
"self": 0.0,
"children": {
"worker_root": {
"total": 2472.4074116529873,
"count": 232033,
"is_parallel": true,
"self": 1168.287186678053,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008494090000112919,
"count": 1,
"is_parallel": true,
"self": 0.0002149350000308914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006344739999804005,
"count": 2,
"is_parallel": true,
"self": 0.0006344739999804005
}
}
},
"UnityEnvironment.step": {
"total": 0.029298243000027924,
"count": 1,
"is_parallel": true,
"self": 0.0003805150000175672,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017592000000377084,
"count": 1,
"is_parallel": true,
"self": 0.00017592000000377084
},
"communicator.exchange": {
"total": 0.028007391000016923,
"count": 1,
"is_parallel": true,
"self": 0.028007391000016923
},
"steps_from_proto": {
"total": 0.0007344169999896621,
"count": 1,
"is_parallel": true,
"self": 0.00019492200004833649,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005394949999413257,
"count": 2,
"is_parallel": true,
"self": 0.0005394949999413257
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1304.1202249749342,
"count": 232032,
"is_parallel": true,
"self": 38.076496952058505,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.68934319089766,
"count": 232032,
"is_parallel": true,
"self": 84.68934319089766
},
"communicator.exchange": {
"total": 1088.5411816460085,
"count": 232032,
"is_parallel": true,
"self": 1088.5411816460085
},
"steps_from_proto": {
"total": 92.81320318596954,
"count": 232032,
"is_parallel": true,
"self": 34.87623573591367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.936967450055874,
"count": 464064,
"is_parallel": true,
"self": 57.936967450055874
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 510.6673986780434,
"count": 232033,
"self": 6.916222772046751,
"children": {
"process_trajectory": {
"total": 161.8706266869973,
"count": 232033,
"self": 160.55575577199681,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3148709150004834,
"count": 10,
"self": 1.3148709150004834
}
}
},
"_update_policy": {
"total": 341.88054921899936,
"count": 97,
"self": 276.92959390099765,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.95095531800172,
"count": 2910,
"self": 64.95095531800172
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.809997780190315e-07,
"count": 1,
"self": 8.809997780190315e-07
},
"TrainerController._save_models": {
"total": 0.1184340129998418,
"count": 1,
"self": 0.001965389999895706,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11646862299994609,
"count": 1,
"self": 0.11646862299994609
}
}
}
}
}
}
}