panos-span's picture
First Push
5c4fab5 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2888856828212738,
"min": 0.2888856828212738,
"max": 1.4329618215560913,
"count": 47
},
"Pyramids.Policy.Entropy.sum": {
"value": 8703.5478515625,
"min": 8703.5478515625,
"max": 43470.328125,
"count": 47
},
"Pyramids.Step.mean": {
"value": 1409952.0,
"min": 29952.0,
"max": 1409952.0,
"count": 47
},
"Pyramids.Step.sum": {
"value": 1409952.0,
"min": 29952.0,
"max": 1409952.0,
"count": 47
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6864576935768127,
"min": -0.3146674931049347,
"max": 0.7545429468154907,
"count": 47
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 195.64044189453125,
"min": -74.5761947631836,
"max": 220.3265380859375,
"count": 47
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0014807706465944648,
"min": -0.014516398310661316,
"max": 0.4305473864078522,
"count": 47
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.4220196306705475,
"min": -3.890394687652588,
"max": 102.03973388671875,
"count": 47
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07098227089625739,
"min": 0.06456907741260436,
"max": 0.0737712859623744,
"count": 47
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9937517925476034,
"min": 0.49812837164406126,
"max": 1.0821096618584467,
"count": 47
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014629635098528871,
"min": 0.00035424602329197583,
"max": 0.01652276612626987,
"count": 47
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2048148913794042,
"min": 0.0049594443260876616,
"max": 0.24369578411079054,
"count": 47
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00016052271077815952,
"min": 0.00016052271077815952,
"max": 0.00029838354339596195,
"count": 47
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.002247317950894233,
"min": 0.0020886848037717336,
"max": 0.0040110732629756,
"count": 47
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.15350755476190478,
"min": 0.15350755476190478,
"max": 0.19946118095238097,
"count": 47
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.149105766666667,
"min": 1.3962282666666668,
"max": 2.7975383000000003,
"count": 47
},
"Pyramids.Policy.Beta.mean": {
"value": 0.005355404720714286,
"min": 0.005355404720714286,
"max": 0.009946171977142856,
"count": 47
},
"Pyramids.Policy.Beta.sum": {
"value": 0.07497566609,
"min": 0.06962320384,
"max": 0.13370873756,
"count": 47
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009138896130025387,
"min": 0.008504475466907024,
"max": 0.44626665115356445,
"count": 47
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12794454395771027,
"min": 0.12235061824321747,
"max": 3.123866558074951,
"count": 47
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 287.7980769230769,
"min": 260.70535714285717,
"max": 999.0,
"count": 47
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29931.0,
"min": 15984.0,
"max": 33757.0,
"count": 47
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.638108556824071,
"min": -1.0000000521540642,
"max": 1.7262545280835846,
"count": 47
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 172.00139846652746,
"min": -29.994401559233665,
"max": 198.9405976831913,
"count": 47
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.638108556824071,
"min": -1.0000000521540642,
"max": 1.7262545280835846,
"count": 47
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 172.00139846652746,
"min": -29.994401559233665,
"max": 198.9405976831913,
"count": 47
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.026772336964010417,
"min": 0.025151664927761885,
"max": 8.498190904036164,
"count": 47
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.8110953812210937,
"min": 2.6193292424140964,
"max": 135.97105446457863,
"count": 47
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 47
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 47
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709826229",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709829327"
},
"total": 3098.2886912880003,
"count": 1,
"self": 0.38516649899975164,
"children": {
"run_training.setup": {
"total": 0.050616000999980315,
"count": 1,
"self": 0.050616000999980315
},
"TrainerController.start_learning": {
"total": 3097.8529087880006,
"count": 1,
"self": 1.8655746649028515,
"children": {
"TrainerController._reset_env": {
"total": 2.1292493260000356,
"count": 1,
"self": 2.1292493260000356
},
"TrainerController.advance": {
"total": 3093.7136924030974,
"count": 90961,
"self": 1.8458166831319431,
"children": {
"env_step": {
"total": 2213.128990104973,
"count": 90961,
"self": 2034.9582265960194,
"children": {
"SubprocessEnvManager._take_step": {
"total": 177.06774468290973,
"count": 90961,
"self": 6.414903056899675,
"children": {
"TorchPolicy.evaluate": {
"total": 170.65284162601006,
"count": 88538,
"self": 170.65284162601006
}
}
},
"workers": {
"total": 1.1030188260440354,
"count": 90960,
"self": 0.0,
"children": {
"worker_root": {
"total": 3091.0109890500676,
"count": 90960,
"is_parallel": true,
"self": 1219.5627201070201,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020017429999370506,
"count": 1,
"is_parallel": true,
"self": 0.0005870719999165885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001414671000020462,
"count": 8,
"is_parallel": true,
"self": 0.001414671000020462
}
}
},
"UnityEnvironment.step": {
"total": 0.04684586100006527,
"count": 1,
"is_parallel": true,
"self": 0.0006361190000916395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004333399999723042,
"count": 1,
"is_parallel": true,
"self": 0.0004333399999723042
},
"communicator.exchange": {
"total": 0.04382504299996981,
"count": 1,
"is_parallel": true,
"self": 0.04382504299996981
},
"steps_from_proto": {
"total": 0.0019513590000315162,
"count": 1,
"is_parallel": true,
"self": 0.00034890299980361306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016024560002279031,
"count": 8,
"is_parallel": true,
"self": 0.0016024560002279031
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1871.4482689430474,
"count": 90959,
"is_parallel": true,
"self": 47.2033367600236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 31.900206358018522,
"count": 90959,
"is_parallel": true,
"self": 31.900206358018522
},
"communicator.exchange": {
"total": 1656.9276957150662,
"count": 90959,
"is_parallel": true,
"self": 1656.9276957150662
},
"steps_from_proto": {
"total": 135.4170301099391,
"count": 90959,
"is_parallel": true,
"self": 26.79890593989353,
"children": {
"_process_rank_one_or_two_observation": {
"total": 108.61812417004558,
"count": 727672,
"is_parallel": true,
"self": 108.61812417004558
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 878.7388856149923,
"count": 90960,
"self": 3.6033029719742444,
"children": {
"process_trajectory": {
"total": 176.6116829040161,
"count": 90960,
"self": 176.41828235701587,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19340054700023757,
"count": 2,
"self": 0.19340054700023757
}
}
},
"_update_policy": {
"total": 698.523899739002,
"count": 654,
"self": 408.11859887297305,
"children": {
"TorchPPOOptimizer.update": {
"total": 290.40530086602894,
"count": 32241,
"self": 290.40530086602894
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4200004443409853e-06,
"count": 1,
"self": 1.4200004443409853e-06
},
"TrainerController._save_models": {
"total": 0.14439097400008905,
"count": 1,
"self": 0.0023381649998555076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14205280900023354,
"count": 1,
"self": 0.14205280900023354
}
}
}
}
}
}
}