ppo-PyramidsRND / run_logs /timers.json
Max100ce's picture
First Push
d670a1d
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4644012749195099,
"min": 0.4644012749195099,
"max": 1.464332938194275,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13909.7470703125,
"min": 13909.7470703125,
"max": 44422.00390625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989935.0,
"min": 29952.0,
"max": 989935.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989935.0,
"min": 29952.0,
"max": 989935.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5809727907180786,
"min": -0.11836423724889755,
"max": 0.6675556898117065,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 163.83433532714844,
"min": -28.644145965576172,
"max": 190.2533721923828,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.013455166481435299,
"min": -0.004178720060735941,
"max": 0.4489738345146179,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.7943570613861084,
"min": -1.1909352540969849,
"max": 106.40679931640625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07208895152653187,
"min": 0.06548332063192945,
"max": 0.0747629781432172,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0092453213714463,
"min": 0.5021661724493807,
"max": 1.0853450082484453,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01734011853700738,
"min": 0.000626654812162345,
"max": 0.01734011853700738,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24276165951810336,
"min": 0.007000351290749133,
"max": 0.242813067297296,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.650568878414293e-06,
"min": 7.650568878414293e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001071079642978001,
"min": 0.0001071079642978001,
"max": 0.0034932994355669,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10255015714285713,
"min": 0.10255015714285713,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4357022,
"min": 1.3691136000000002,
"max": 2.5276371,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002647606985714288,
"min": 0.0002647606985714288,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003706649780000003,
"min": 0.003706649780000003,
"max": 0.11645686669,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01052778959274292,
"min": 0.01052778959274292,
"max": 0.6269509196281433,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14738905429840088,
"min": 0.14738905429840088,
"max": 4.3886566162109375,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 301.0,
"min": 281.13084112149534,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28294.0,
"min": 15984.0,
"max": 32142.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6765347215690112,
"min": -1.0000000521540642,
"max": 1.680630171847231,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 159.27079854905605,
"min": -32.000001668930054,
"max": 178.14679821580648,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6765347215690112,
"min": -1.0000000521540642,
"max": 1.680630171847231,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 159.27079854905605,
"min": -32.000001668930054,
"max": 178.14679821580648,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03247837294076913,
"min": 0.03247837294076913,
"max": 13.82760770432651,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.085445429373067,
"min": 3.085445429373067,
"max": 221.24172326922417,
"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": "1678753059",
"python_version": "3.8.16 (default, Jan 17 2023, 23:13:24) \n[GCC 11.2.0]",
"command_line_arguments": "/anaconda/bin//mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.20.0",
"end_time_seconds": "1678754918"
},
"total": 1858.3480585590005,
"count": 1,
"self": 1.933366475001094,
"children": {
"run_training.setup": {
"total": 0.024146462998032803,
"count": 1,
"self": 0.024146462998032803
},
"TrainerController.start_learning": {
"total": 1856.3905456210014,
"count": 1,
"self": 1.3790071217190416,
"children": {
"TrainerController._reset_env": {
"total": 3.778087778999179,
"count": 1,
"self": 3.778087778999179
},
"TrainerController.advance": {
"total": 1851.147607072282,
"count": 63961,
"self": 1.4454659469847684,
"children": {
"env_step": {
"total": 1132.4269303228284,
"count": 63961,
"self": 1023.305422506477,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.21083544686553,
"count": 63961,
"self": 4.268967457952385,
"children": {
"TorchPolicy.evaluate": {
"total": 103.94186798891315,
"count": 62574,
"self": 37.412063954689074,
"children": {
"TorchPolicy.sample_actions": {
"total": 66.52980403422407,
"count": 62574,
"self": 66.52980403422407
}
}
}
}
},
"workers": {
"total": 0.9106723694858374,
"count": 63961,
"self": 0.0,
"children": {
"worker_root": {
"total": 1854.2788956917866,
"count": 63961,
"is_parallel": true,
"self": 933.1679501399158,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019366359993000515,
"count": 1,
"is_parallel": true,
"self": 0.0004408100030559581,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014958259962440934,
"count": 8,
"is_parallel": true,
"self": 0.0014958259962440934
}
}
},
"UnityEnvironment.step": {
"total": 0.03267618899917579,
"count": 1,
"is_parallel": true,
"self": 0.0003273069960414432,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002784810021694284,
"count": 1,
"is_parallel": true,
"self": 0.0002784810021694284
},
"communicator.exchange": {
"total": 0.03106808500160696,
"count": 1,
"is_parallel": true,
"self": 0.03106808500160696
},
"steps_from_proto": {
"total": 0.0010023159993579611,
"count": 1,
"is_parallel": true,
"self": 0.00025743299920577556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007448830001521856,
"count": 8,
"is_parallel": true,
"self": 0.0007448830001521856
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 921.1109455518708,
"count": 63960,
"is_parallel": true,
"self": 30.257230110226374,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 18.439275586213626,
"count": 63960,
"is_parallel": true,
"self": 18.439275586213626
},
"communicator.exchange": {
"total": 796.300585318997,
"count": 63960,
"is_parallel": true,
"self": 796.300585318997
},
"steps_from_proto": {
"total": 76.11385453643379,
"count": 63960,
"is_parallel": true,
"self": 15.700107173342985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.413747363090806,
"count": 511680,
"is_parallel": true,
"self": 60.413747363090806
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 717.2752108024688,
"count": 63961,
"self": 2.354150046547147,
"children": {
"process_trajectory": {
"total": 148.88929317789734,
"count": 63961,
"self": 148.20108118389908,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6882119939982658,
"count": 2,
"self": 0.6882119939982658
}
}
},
"_update_policy": {
"total": 566.0317675780243,
"count": 450,
"self": 213.70350251671698,
"children": {
"TorchPPOOptimizer.update": {
"total": 352.3282650613073,
"count": 22827,
"self": 352.3282650613073
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.749993867240846e-07,
"count": 1,
"self": 8.749993867240846e-07
},
"TrainerController._save_models": {
"total": 0.08584277300178655,
"count": 1,
"self": 0.0016637320004520006,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08417904100133455,
"count": 1,
"self": 0.08417904100133455
}
}
}
}
}
}
}