ppo-PyramidsRND / run_logs /timers.json
Sookeyy's picture
push to hub
22a734e
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3252579867839813,
"min": 0.3235195577144623,
"max": 1.453179955482483,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9726.5146484375,
"min": 9638.294921875,
"max": 44083.66796875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989964.0,
"min": 29879.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989964.0,
"min": 29879.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4424925446510315,
"min": -0.10434960573911667,
"max": 0.5264735221862793,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 118.1455078125,
"min": -25.14825439453125,
"max": 145.83316040039062,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.050865545868873596,
"min": -0.010932265780866146,
"max": 0.2839398682117462,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 13.581100463867188,
"min": -2.7549309730529785,
"max": 67.29374694824219,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06986476316454908,
"min": 0.06598236975727208,
"max": 0.07561312551193596,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9781066843036872,
"min": 0.6049050040954876,
"max": 1.0721081706190794,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01465011511408236,
"min": 0.0004442056894169132,
"max": 0.015164360227312762,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20510161159715304,
"min": 0.0053304682730029584,
"max": 0.21230104318237866,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.5946403256285685e-06,
"min": 7.5946403256285685e-06,
"max": 0.0002948482142172625,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010632496455879996,
"min": 0.00010632496455879996,
"max": 0.0033827849724051,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253151428571429,
"min": 0.10253151428571429,
"max": 0.19828273749999997,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354412,
"min": 1.4354412,
"max": 2.5275949,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002628982771428571,
"min": 0.0002628982771428571,
"max": 0.00982844547625,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003680575879999999,
"min": 0.003680575879999999,
"max": 0.11278673051,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01269929762929678,
"min": 0.01269929762929678,
"max": 0.4024084210395813,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17779016494750977,
"min": 0.17779016494750977,
"max": 3.2192673683166504,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 381.2739726027397,
"min": 349.0886075949367,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27833.0,
"min": 16422.0,
"max": 32801.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.560577757863535,
"min": -0.999987552408129,
"max": 1.6255822546685799,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 112.36159856617451,
"min": -31.999601677060127,
"max": 129.5491985604167,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.560577757863535,
"min": -0.999987552408129,
"max": 1.6255822546685799,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 112.36159856617451,
"min": -31.999601677060127,
"max": 129.5491985604167,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.051165715402425524,
"min": 0.04795081116763073,
"max": 8.216747816871194,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.683931508974638,
"min": 3.683931508974638,
"max": 139.6847128868103,
"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": "1691080668",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1691082887"
},
"total": 2218.554568293,
"count": 1,
"self": 0.5269482050002807,
"children": {
"run_training.setup": {
"total": 0.06105930600006104,
"count": 1,
"self": 0.06105930600006104
},
"TrainerController.start_learning": {
"total": 2217.9665607819998,
"count": 1,
"self": 1.3793323059881004,
"children": {
"TrainerController._reset_env": {
"total": 5.182051232000049,
"count": 1,
"self": 5.182051232000049
},
"TrainerController.advance": {
"total": 2211.3076113940115,
"count": 63614,
"self": 1.3156689509692114,
"children": {
"env_step": {
"total": 1552.6022696659538,
"count": 63614,
"self": 1445.1393302629263,
"children": {
"SubprocessEnvManager._take_step": {
"total": 106.65005668809908,
"count": 63614,
"self": 4.658920591068181,
"children": {
"TorchPolicy.evaluate": {
"total": 101.9911360970309,
"count": 62558,
"self": 101.9911360970309
}
}
},
"workers": {
"total": 0.8128827149284916,
"count": 63614,
"self": 0.0,
"children": {
"worker_root": {
"total": 2212.8671464289787,
"count": 63614,
"is_parallel": true,
"self": 880.6701716489783,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025281180001002213,
"count": 1,
"is_parallel": true,
"self": 0.0006913290003467409,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018367889997534803,
"count": 8,
"is_parallel": true,
"self": 0.0018367889997534803
}
}
},
"UnityEnvironment.step": {
"total": 0.048955097000089154,
"count": 1,
"is_parallel": true,
"self": 0.0005765220003013383,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048753900000519934,
"count": 1,
"is_parallel": true,
"self": 0.00048753900000519934
},
"communicator.exchange": {
"total": 0.04595208899991121,
"count": 1,
"is_parallel": true,
"self": 0.04595208899991121
},
"steps_from_proto": {
"total": 0.0019389469998714048,
"count": 1,
"is_parallel": true,
"self": 0.0003766189984162338,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001562328001455171,
"count": 8,
"is_parallel": true,
"self": 0.001562328001455171
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1332.1969747800003,
"count": 63613,
"is_parallel": true,
"self": 34.32032255804688,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.27197461302967,
"count": 63613,
"is_parallel": true,
"self": 23.27197461302967
},
"communicator.exchange": {
"total": 1168.8246740198879,
"count": 63613,
"is_parallel": true,
"self": 1168.8246740198879
},
"steps_from_proto": {
"total": 105.78000358903591,
"count": 63613,
"is_parallel": true,
"self": 20.648237055858317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.1317665331776,
"count": 508904,
"is_parallel": true,
"self": 85.1317665331776
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 657.3896727770884,
"count": 63614,
"self": 2.5455548610643746,
"children": {
"process_trajectory": {
"total": 108.5161281380233,
"count": 63614,
"self": 108.22954282502315,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28658531300015966,
"count": 2,
"self": 0.28658531300015966
}
}
},
"_update_policy": {
"total": 546.3279897780008,
"count": 449,
"self": 357.8409215240208,
"children": {
"TorchPPOOptimizer.update": {
"total": 188.48706825397994,
"count": 22833,
"self": 188.48706825397994
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.650002539274283e-07,
"count": 1,
"self": 9.650002539274283e-07
},
"TrainerController._save_models": {
"total": 0.09756488499988336,
"count": 1,
"self": 0.0013300049995450536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09623488000033831,
"count": 1,
"self": 0.09623488000033831
}
}
}
}
}
}
}