ppo-Huggy / run_logs /timers.json
michael-go's picture
Huggy
7c58b7d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4021459817886353,
"min": 1.4021459817886353,
"max": 1.4258842468261719,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69861.921875,
"min": 68550.5546875,
"max": 78371.2109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.0,
"min": 74.23573573573573,
"max": 439.7739130434783,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49364.0,
"min": 48897.0,
"max": 50574.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49939.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49939.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4980692863464355,
"min": 0.12867937982082367,
"max": 2.5565152168273926,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1503.837646484375,
"min": 14.669448852539062,
"max": 1629.7099609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.854443455752344,
"min": 1.9416741090908385,
"max": 4.051378913320865,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2320.374960362911,
"min": 221.3508484363556,
"max": 2551.0835668444633,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.854443455752344,
"min": 1.9416741090908385,
"max": 4.051378913320865,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2320.374960362911,
"min": 221.3508484363556,
"max": 2551.0835668444633,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01593064222243912,
"min": 0.013119713903870433,
"max": 0.020515369743225167,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04779192666731736,
"min": 0.027348311910949025,
"max": 0.05917248782606445,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06299069416191842,
"min": 0.02055018950874607,
"max": 0.06381221314271292,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18897208248575526,
"min": 0.04110037901749214,
"max": 0.19143663942813874,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7378487540833396e-06,
"min": 3.7378487540833396e-06,
"max": 0.00029526900157699995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.121354626225002e-05,
"min": 1.121354626225002e-05,
"max": 0.0008437461187512998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012459166666667,
"min": 0.1012459166666667,
"max": 0.19842300000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037377500000001,
"min": 0.20764065000000004,
"max": 0.5812487000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.217124166666678e-05,
"min": 7.217124166666678e-05,
"max": 0.0049213077,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021651372500000032,
"min": 0.00021651372500000032,
"max": 0.014064310129999997,
"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": "1727843953",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727846429"
},
"total": 2476.328290945,
"count": 1,
"self": 0.42534046999981,
"children": {
"run_training.setup": {
"total": 0.0651021830000218,
"count": 1,
"self": 0.0651021830000218
},
"TrainerController.start_learning": {
"total": 2475.837848292,
"count": 1,
"self": 4.34487980310314,
"children": {
"TrainerController._reset_env": {
"total": 2.263514590999989,
"count": 1,
"self": 2.263514590999989
},
"TrainerController.advance": {
"total": 2469.1122759478976,
"count": 232941,
"self": 4.565067835891568,
"children": {
"env_step": {
"total": 1959.1819516989103,
"count": 232941,
"self": 1547.6880345151374,
"children": {
"SubprocessEnvManager._take_step": {
"total": 408.7387612568659,
"count": 232941,
"self": 15.956037349851954,
"children": {
"TorchPolicy.evaluate": {
"total": 392.782723907014,
"count": 222958,
"self": 392.782723907014
}
}
},
"workers": {
"total": 2.7551559269070367,
"count": 232941,
"self": 0.0,
"children": {
"worker_root": {
"total": 2468.5564608749105,
"count": 232941,
"is_parallel": true,
"self": 1214.1572248450873,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008603590000575423,
"count": 1,
"is_parallel": true,
"self": 0.00021530499998334562,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006450540000741967,
"count": 2,
"is_parallel": true,
"self": 0.0006450540000741967
}
}
},
"UnityEnvironment.step": {
"total": 0.02974706099996638,
"count": 1,
"is_parallel": true,
"self": 0.00038025799995011766,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019613699998899392,
"count": 1,
"is_parallel": true,
"self": 0.00019613699998899392
},
"communicator.exchange": {
"total": 0.028406979000010324,
"count": 1,
"is_parallel": true,
"self": 0.028406979000010324
},
"steps_from_proto": {
"total": 0.0007636870000169438,
"count": 1,
"is_parallel": true,
"self": 0.00022828599992408272,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005354010000928611,
"count": 2,
"is_parallel": true,
"self": 0.0005354010000928611
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1254.3992360298232,
"count": 232940,
"is_parallel": true,
"self": 37.69352945697551,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.53958984301278,
"count": 232940,
"is_parallel": true,
"self": 83.53958984301278
},
"communicator.exchange": {
"total": 1043.3241718949291,
"count": 232940,
"is_parallel": true,
"self": 1043.3241718949291
},
"steps_from_proto": {
"total": 89.8419448349058,
"count": 232940,
"is_parallel": true,
"self": 33.58449973587358,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.257445099032225,
"count": 465880,
"is_parallel": true,
"self": 56.257445099032225
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.3652564130956,
"count": 232941,
"self": 6.491244492061469,
"children": {
"process_trajectory": {
"total": 168.59789767803443,
"count": 232941,
"self": 167.18183234003425,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4160653380001804,
"count": 10,
"self": 1.4160653380001804
}
}
},
"_update_policy": {
"total": 330.2761142429997,
"count": 97,
"self": 264.1623779829939,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.1137362600058,
"count": 2910,
"self": 66.1137362600058
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.339996722701471e-07,
"count": 1,
"self": 9.339996722701471e-07
},
"TrainerController._save_models": {
"total": 0.11717701599991415,
"count": 1,
"self": 0.001912777000143251,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1152642389997709,
"count": 1,
"self": 0.1152642389997709
}
}
}
}
}
}
}