ppo-PyramidsRND / run_logs /timers.json
labicquette's picture
First Push
ce3b19d
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.43755093216896057,
"min": 0.43755093216896057,
"max": 1.5025429725646973,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13238.541015625,
"min": 13205.345703125,
"max": 45581.14453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989956.0,
"min": 29952.0,
"max": 989956.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989956.0,
"min": 29952.0,
"max": 989956.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.2815815806388855,
"min": -0.15373407304286957,
"max": 0.3029116690158844,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 73.21121215820312,
"min": -36.434974670410156,
"max": 78.4541244506836,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.3829507529735565,
"min": -0.3829507529735565,
"max": 0.32529014348983765,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -99.56719207763672,
"min": -99.56719207763672,
"max": 77.09376525878906,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07028215841934116,
"min": 0.06550244176871912,
"max": 0.0740713168858862,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9839502178707762,
"min": 0.5045029557960365,
"max": 1.0411508640231035,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.04525686614761581,
"min": 0.0004458821553389409,
"max": 0.04525686614761581,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.6335961260666213,
"min": 0.004630907636347332,
"max": 0.6335961260666213,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4453475182499995e-06,
"min": 7.4453475182499995e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001042348652555,
"min": 0.0001042348652555,
"max": 0.0033819317726895004,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248175000000001,
"min": 0.10248175000000001,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4347445,
"min": 1.3886848,
"max": 2.5274283,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000257926825,
"min": 0.000257926825,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00361097555,
"min": 0.00361097555,
"max": 0.11275831894999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012306400574743748,
"min": 0.012306400574743748,
"max": 0.4373604655265808,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17228960990905762,
"min": 0.17228960990905762,
"max": 3.061523199081421,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 567.8275862068965,
"min": 500.6181818181818,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32934.0,
"min": 15984.0,
"max": 32995.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.0527482416866154,
"min": -1.0000000521540642,
"max": 1.1356326964768497,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 61.059398017823696,
"min": -31.00000161677599,
"max": 65.55579797178507,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.0527482416866154,
"min": -1.0000000521540642,
"max": 1.1356326964768497,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 61.059398017823696,
"min": -31.00000161677599,
"max": 65.55579797178507,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07180431509262016,
"min": 0.06757959061281078,
"max": 8.600069225765765,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.164650275371969,
"min": 3.5448112203739583,
"max": 137.60110761225224,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1683970714",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1683972727"
},
"total": 2013.8753095320003,
"count": 1,
"self": 1.1403367759999128,
"children": {
"run_training.setup": {
"total": 0.04273042100021485,
"count": 1,
"self": 0.04273042100021485
},
"TrainerController.start_learning": {
"total": 2012.6922423350002,
"count": 1,
"self": 1.3458508870389778,
"children": {
"TrainerController._reset_env": {
"total": 3.851147917000162,
"count": 1,
"self": 3.851147917000162
},
"TrainerController.advance": {
"total": 2007.3510245169605,
"count": 63344,
"self": 1.3277804779422695,
"children": {
"env_step": {
"total": 1371.3804297330062,
"count": 63344,
"self": 1263.821765572015,
"children": {
"SubprocessEnvManager._take_step": {
"total": 106.77381857902219,
"count": 63344,
"self": 4.645671559098446,
"children": {
"TorchPolicy.evaluate": {
"total": 102.12814701992374,
"count": 62561,
"self": 102.12814701992374
}
}
},
"workers": {
"total": 0.7848455819689661,
"count": 63344,
"self": 0.0,
"children": {
"worker_root": {
"total": 2008.1065769339111,
"count": 63344,
"is_parallel": true,
"self": 852.7240131638605,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017767899998943903,
"count": 1,
"is_parallel": true,
"self": 0.0005780619994766312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011987280004177592,
"count": 8,
"is_parallel": true,
"self": 0.0011987280004177592
}
}
},
"UnityEnvironment.step": {
"total": 0.05178666600022552,
"count": 1,
"is_parallel": true,
"self": 0.0005276590004541504,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005036129996369709,
"count": 1,
"is_parallel": true,
"self": 0.0005036129996369709
},
"communicator.exchange": {
"total": 0.04899160600007235,
"count": 1,
"is_parallel": true,
"self": 0.04899160600007235
},
"steps_from_proto": {
"total": 0.0017637880000620498,
"count": 1,
"is_parallel": true,
"self": 0.0003576720000637579,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001406115999998292,
"count": 8,
"is_parallel": true,
"self": 0.001406115999998292
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1155.3825637700506,
"count": 63343,
"is_parallel": true,
"self": 31.32650870513453,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.648422909969213,
"count": 63343,
"is_parallel": true,
"self": 22.648422909969213
},
"communicator.exchange": {
"total": 1005.2715101399403,
"count": 63343,
"is_parallel": true,
"self": 1005.2715101399403
},
"steps_from_proto": {
"total": 96.13612201500655,
"count": 63343,
"is_parallel": true,
"self": 19.437641789935697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.69848022507085,
"count": 506744,
"is_parallel": true,
"self": 76.69848022507085
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 634.642814306012,
"count": 63344,
"self": 2.448966017966086,
"children": {
"process_trajectory": {
"total": 103.81511690305251,
"count": 63344,
"self": 103.59843575805235,
"children": {
"RLTrainer._checkpoint": {
"total": 0.216681145000166,
"count": 2,
"self": 0.216681145000166
}
}
},
"_update_policy": {
"total": 528.3787313849934,
"count": 443,
"self": 344.4265459409794,
"children": {
"TorchPPOOptimizer.update": {
"total": 183.95218544401405,
"count": 22791,
"self": 183.95218544401405
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3910002962802537e-06,
"count": 1,
"self": 1.3910002962802537e-06
},
"TrainerController._save_models": {
"total": 0.14421762300025875,
"count": 1,
"self": 0.0019519070001479122,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14226571600011084,
"count": 1,
"self": 0.14226571600011084
}
}
}
}
}
}
}