ppo-Huggy / run_logs /timers.json
Claaas's picture
Huggy
88dcad5
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4259545803070068,
"min": 1.4198740720748901,
"max": 1.4259545803070068,
"count": 6
},
"Huggy.Policy.Entropy.sum": {
"value": 71089.5390625,
"min": 69172.2734375,
"max": 78534.65625,
"count": 6
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 160.6290322580645,
"min": 160.6290322580645,
"max": 368.77941176470586,
"count": 6
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49795.0,
"min": 49519.0,
"max": 50154.0,
"count": 6
},
"Huggy.Step.mean": {
"value": 299963.0,
"min": 49885.0,
"max": 299963.0,
"count": 6
},
"Huggy.Step.sum": {
"value": 299963.0,
"min": 49885.0,
"max": 299963.0,
"count": 6
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.4954533576965332,
"min": 0.1715380847454071,
"max": 1.4954533576965332,
"count": 6
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 463.5905456542969,
"min": 23.157642364501953,
"max": 463.5905456542969,
"count": 6
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.478076188987301,
"min": 1.8233734027103141,
"max": 3.5086319914553314,
"count": 6
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1078.2036185860634,
"min": 246.1554093658924,
"max": 1078.2036185860634,
"count": 6
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.478076188987301,
"min": 1.8233734027103141,
"max": 3.5086319914553314,
"count": 6
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1078.2036185860634,
"min": 246.1554093658924,
"max": 1078.2036185860634,
"count": 6
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019604676798674822,
"min": 0.01493028273131737,
"max": 0.020642197086514595,
"count": 6
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.039209353597349644,
"min": 0.02986056546263474,
"max": 0.052283507785614344,
"count": 6
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03594618175799648,
"min": 0.020260032545775176,
"max": 0.03594618175799648,
"count": 6
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07189236351599296,
"min": 0.04052006509155035,
"max": 0.08180487013111512,
"count": 6
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.0002580839389720249,
"min": 0.0002580839389720249,
"max": 0.000295305826564725,
"count": 6
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.0005161678779440498,
"min": 0.0005161678779440498,
"max": 0.0008438443687185499,
"count": 6
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.186027975,
"min": 0.186027975,
"max": 0.19843527500000002,
"count": 6
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.37205595,
"min": 0.37205595,
"max": 0.58128145,
"count": 6
},
"Huggy.Policy.Beta.mean": {
"value": 0.004302795952500001,
"min": 0.004302795952500001,
"max": 0.004921920222500001,
"count": 6
},
"Huggy.Policy.Beta.sum": {
"value": 0.008605591905000001,
"min": 0.008605591905000001,
"max": 0.014065944354999999,
"count": 6
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 6
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 6
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1689834473",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689834828"
},
"total": 354.52661724800004,
"count": 1,
"self": 0.4450507570000468,
"children": {
"run_training.setup": {
"total": 0.033703663000039796,
"count": 1,
"self": 0.033703663000039796
},
"TrainerController.start_learning": {
"total": 354.04786282799995,
"count": 1,
"self": 0.6223972070093282,
"children": {
"TrainerController._reset_env": {
"total": 5.16579864199997,
"count": 1,
"self": 5.16579864199997
},
"TrainerController.advance": {
"total": 347.8673989019906,
"count": 34253,
"self": 0.6392635750162299,
"children": {
"env_step": {
"total": 270.7414015929824,
"count": 34253,
"self": 227.8446626439765,
"children": {
"SubprocessEnvManager._take_step": {
"total": 42.49328462400803,
"count": 34253,
"self": 2.5922277860236704,
"children": {
"TorchPolicy.evaluate": {
"total": 39.901056837984356,
"count": 33633,
"self": 39.901056837984356
}
}
},
"workers": {
"total": 0.40345432499788103,
"count": 34252,
"self": 0.0,
"children": {
"worker_root": {
"total": 352.63488022200244,
"count": 34252,
"is_parallel": true,
"self": 166.63533792799882,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008859210000196072,
"count": 1,
"is_parallel": true,
"self": 0.0002543170000421924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006316039999774148,
"count": 2,
"is_parallel": true,
"self": 0.0006316039999774148
}
}
},
"UnityEnvironment.step": {
"total": 0.028596880999998575,
"count": 1,
"is_parallel": true,
"self": 0.00032674500005214213,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002252819999739586,
"count": 1,
"is_parallel": true,
"self": 0.0002252819999739586
},
"communicator.exchange": {
"total": 0.027350028999990172,
"count": 1,
"is_parallel": true,
"self": 0.027350028999990172
},
"steps_from_proto": {
"total": 0.000694824999982302,
"count": 1,
"is_parallel": true,
"self": 0.00020508099999005935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004897439999922426,
"count": 2,
"is_parallel": true,
"self": 0.0004897439999922426
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 185.99954229400362,
"count": 34251,
"is_parallel": true,
"self": 5.900845499006948,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.00319727598685,
"count": 34251,
"is_parallel": true,
"self": 12.00319727598685
},
"communicator.exchange": {
"total": 154.11324830600557,
"count": 34251,
"is_parallel": true,
"self": 154.11324830600557
},
"steps_from_proto": {
"total": 13.982251213004247,
"count": 34251,
"is_parallel": true,
"self": 5.07903137800605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 8.903219834998197,
"count": 68502,
"is_parallel": true,
"self": 8.903219834998197
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 76.48673373399197,
"count": 34252,
"self": 0.967087231980372,
"children": {
"process_trajectory": {
"total": 15.985832506011661,
"count": 34252,
"self": 15.793919199011611,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19191330700004983,
"count": 1,
"self": 0.19191330700004983
}
}
},
"_update_policy": {
"total": 59.533813995999935,
"count": 14,
"self": 50.937078630000315,
"children": {
"TorchPPOOptimizer.update": {
"total": 8.59673536599962,
"count": 420,
"self": 8.59673536599962
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4729999975315877e-06,
"count": 1,
"self": 1.4729999975315877e-06
},
"TrainerController._save_models": {
"total": 0.3922666040000422,
"count": 1,
"self": 0.004854493000038929,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3874121110000033,
"count": 1,
"self": 0.3874121110000033
}
}
}
}
}
}
}