miguepez's picture
First Push
49ea815 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5825960040092468,
"min": 0.5825960040092468,
"max": 1.3693597316741943,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17319.4140625,
"min": 17319.4140625,
"max": 41540.8984375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989907.0,
"min": 29952.0,
"max": 989907.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989907.0,
"min": 29952.0,
"max": 989907.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.17000553011894226,
"min": -0.10237380117177963,
"max": 0.17487314343452454,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 42.841392517089844,
"min": -24.672086715698242,
"max": 44.068031311035156,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03349735215306282,
"min": -0.03775889798998833,
"max": 0.23130881786346436,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.441332817077637,
"min": -9.515242576599121,
"max": 54.8201904296875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0688871013477356,
"min": 0.06398348254021205,
"max": 0.07127854240980112,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9644194188682983,
"min": 0.4748306819813155,
"max": 1.024191436377199,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.009264409751354142,
"min": 8.306123901096976e-05,
"max": 0.010437345676099354,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.12970173651895797,
"min": 0.001079796107142607,
"max": 0.14612283946539095,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.0298240282607146e-05,
"min": 1.0298240282607146e-05,
"max": 0.0003935341730450286,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00014417536395650005,
"min": 0.00014417536395650005,
"max": 0.0046761530309618,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10257453571428572,
"min": 0.10257453571428572,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4360435,
"min": 1.3886848,
"max": 2.5690382,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002671961178571429,
"min": 0.0002671961178571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003740745650000001,
"min": 0.003740745650000001,
"max": 0.11692691617999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009195574559271336,
"min": 0.009091311134397984,
"max": 0.3728086054325104,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12873804569244385,
"min": 0.12727835774421692,
"max": 2.6096601486206055,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 630.2666666666667,
"min": 630.2666666666667,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28362.0,
"min": 15984.0,
"max": 32592.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.7473332929942343,
"min": -1.0000000521540642,
"max": 0.7856464723861495,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 33.62999818474054,
"min": -31.996801674365997,
"max": 33.78279831260443,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.7473332929942343,
"min": -1.0000000521540642,
"max": 0.7856464723861495,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 33.62999818474054,
"min": -31.996801674365997,
"max": 33.78279831260443,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.060560930735341065,
"min": 0.060560930735341065,
"max": 7.026756351813674,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.725241883090348,
"min": 2.725241883090348,
"max": 112.42810162901878,
"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": "1748415332",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748417438"
},
"total": 2105.4824186920005,
"count": 1,
"self": 0.4816766030007784,
"children": {
"run_training.setup": {
"total": 0.03150303500001428,
"count": 1,
"self": 0.03150303500001428
},
"TrainerController.start_learning": {
"total": 2104.9692390539994,
"count": 1,
"self": 1.2374869200425564,
"children": {
"TrainerController._reset_env": {
"total": 2.3277658150000207,
"count": 1,
"self": 2.3277658150000207
},
"TrainerController.advance": {
"total": 2101.322529354957,
"count": 63170,
"self": 1.2985870847769547,
"children": {
"env_step": {
"total": 1431.817105423114,
"count": 63170,
"self": 1285.4058171931138,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.6688582160234,
"count": 63170,
"self": 4.397099916011712,
"children": {
"TorchPolicy.evaluate": {
"total": 141.2717583000117,
"count": 62562,
"self": 141.2717583000117
}
}
},
"workers": {
"total": 0.7424300139769002,
"count": 63170,
"self": 0.0,
"children": {
"worker_root": {
"total": 2100.346174172046,
"count": 63170,
"is_parallel": true,
"self": 921.1965484950708,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018809609998697852,
"count": 1,
"is_parallel": true,
"self": 0.0006110040001203743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001269956999749411,
"count": 8,
"is_parallel": true,
"self": 0.001269956999749411
}
}
},
"UnityEnvironment.step": {
"total": 0.05196915600004104,
"count": 1,
"is_parallel": true,
"self": 0.0005271039999570348,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004768280000462255,
"count": 1,
"is_parallel": true,
"self": 0.0004768280000462255
},
"communicator.exchange": {
"total": 0.049401467000052435,
"count": 1,
"is_parallel": true,
"self": 0.049401467000052435
},
"steps_from_proto": {
"total": 0.001563756999985344,
"count": 1,
"is_parallel": true,
"self": 0.0003306459996110789,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012331110003742651,
"count": 8,
"is_parallel": true,
"self": 0.0012331110003742651
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1179.1496256769753,
"count": 63169,
"is_parallel": true,
"self": 30.596454901975903,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.782765058031146,
"count": 63169,
"is_parallel": true,
"self": 22.782765058031146
},
"communicator.exchange": {
"total": 1034.5671995590005,
"count": 63169,
"is_parallel": true,
"self": 1034.5671995590005
},
"steps_from_proto": {
"total": 91.20320615796777,
"count": 63169,
"is_parallel": true,
"self": 17.748740249020557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.45446590894721,
"count": 505352,
"is_parallel": true,
"self": 73.45446590894721
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 668.2068368470661,
"count": 63170,
"self": 2.3202462111100886,
"children": {
"process_trajectory": {
"total": 124.81529989895898,
"count": 63170,
"self": 124.62290157595817,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19239832300081616,
"count": 2,
"self": 0.19239832300081616
}
}
},
"_update_policy": {
"total": 541.0712907369971,
"count": 440,
"self": 299.8500911910601,
"children": {
"TorchPPOOptimizer.update": {
"total": 241.221199545937,
"count": 22785,
"self": 241.221199545937
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.150000212481245e-07,
"count": 1,
"self": 8.150000212481245e-07
},
"TrainerController._save_models": {
"total": 0.08145614899967768,
"count": 1,
"self": 0.0013622569995277445,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08009389200014994,
"count": 1,
"self": 0.08009389200014994
}
}
}
}
}
}
}