janzw's picture
First Try
b57ab53
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.42341718077659607,
"min": 0.418194979429245,
"max": 1.3877934217453003,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12736.388671875,
"min": 12539.158203125,
"max": 42100.1015625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989877.0,
"min": 29942.0,
"max": 989877.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989877.0,
"min": 29942.0,
"max": 989877.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.548646092414856,
"min": -0.09157144278287888,
"max": 0.6264916658401489,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 151.9749755859375,
"min": -21.97714614868164,
"max": 177.29714965820312,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.21493864059448242,
"min": -0.0008508237660862505,
"max": 0.26964160799980164,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 59.538002014160156,
"min": -0.2212141752243042,
"max": 64.7139892578125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06970484776002372,
"min": 0.06593531215409146,
"max": 0.07314382307323421,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0455727164003559,
"min": 0.5851505845858737,
"max": 1.0455727164003559,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.02000142344179658,
"min": 0.0008535513262964517,
"max": 0.02000142344179658,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.3000213516269487,
"min": 0.011096167241853873,
"max": 0.3000213516269487,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.509077497006671e-06,
"min": 7.509077497006671e-06,
"max": 0.000294765526744825,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011263616245510007,
"min": 0.00011263616245510007,
"max": 0.0036091752969415994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250299333333333,
"min": 0.10250299333333333,
"max": 0.198255175,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5375449,
"min": 1.4781236000000002,
"max": 2.617346,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002600490340000002,
"min": 0.0002600490340000002,
"max": 0.009825691982499999,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003900735510000003,
"min": 0.003900735510000003,
"max": 0.12031553416000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009924997575581074,
"min": 0.009924997575581074,
"max": 0.4233850836753845,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14887496829032898,
"min": 0.1415395438671112,
"max": 3.387080669403076,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 341.9222222222222,
"min": 283.28846153846155,
"max": 995.3548387096774,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30773.0,
"min": 16868.0,
"max": 32021.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5913888652291563,
"min": -0.931716181818516,
"max": 1.6802021124737059,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 143.22499787062407,
"min": -29.593601636588573,
"max": 170.653198890388,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5913888652291563,
"min": -0.931716181818516,
"max": 1.6802021124737059,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 143.22499787062407,
"min": -29.593601636588573,
"max": 170.653198890388,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03467234240363016,
"min": 0.030285189243019966,
"max": 7.700989050997628,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.120510816326714,
"min": 3.0053854822181165,
"max": 138.6178029179573,
"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": "1679252150",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679254309"
},
"total": 2158.84954975,
"count": 1,
"self": 0.4246978820001459,
"children": {
"run_training.setup": {
"total": 0.0981402130000788,
"count": 1,
"self": 0.0981402130000788
},
"TrainerController.start_learning": {
"total": 2158.3267116549996,
"count": 1,
"self": 1.2161991220214077,
"children": {
"TrainerController._reset_env": {
"total": 6.875199716999759,
"count": 1,
"self": 6.875199716999759
},
"TrainerController.advance": {
"total": 2150.1450116919787,
"count": 63984,
"self": 1.3173167138670578,
"children": {
"env_step": {
"total": 1539.6015652161045,
"count": 63984,
"self": 1436.7982002731987,
"children": {
"SubprocessEnvManager._take_step": {
"total": 102.01938092190494,
"count": 63984,
"self": 4.521233198837763,
"children": {
"TorchPolicy.evaluate": {
"total": 97.49814772306718,
"count": 62560,
"self": 97.49814772306718
}
}
},
"workers": {
"total": 0.7839840210008333,
"count": 63984,
"self": 0.0,
"children": {
"worker_root": {
"total": 2153.975334352982,
"count": 63984,
"is_parallel": true,
"self": 827.8560613450322,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019923790000575536,
"count": 1,
"is_parallel": true,
"self": 0.0006483510001089599,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013440279999485938,
"count": 8,
"is_parallel": true,
"self": 0.0013440279999485938
}
}
},
"UnityEnvironment.step": {
"total": 0.05256446700013839,
"count": 1,
"is_parallel": true,
"self": 0.0005155399999239307,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004609770003298763,
"count": 1,
"is_parallel": true,
"self": 0.0004609770003298763
},
"communicator.exchange": {
"total": 0.049937718999899516,
"count": 1,
"is_parallel": true,
"self": 0.049937718999899516
},
"steps_from_proto": {
"total": 0.0016502309999850695,
"count": 1,
"is_parallel": true,
"self": 0.000377758000013273,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012724729999717965,
"count": 8,
"is_parallel": true,
"self": 0.0012724729999717965
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1326.1192730079497,
"count": 63983,
"is_parallel": true,
"self": 30.219072668041463,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.68676284703224,
"count": 63983,
"is_parallel": true,
"self": 22.68676284703224
},
"communicator.exchange": {
"total": 1181.1798815538868,
"count": 63983,
"is_parallel": true,
"self": 1181.1798815538868
},
"steps_from_proto": {
"total": 92.03355593898914,
"count": 63983,
"is_parallel": true,
"self": 19.64122538417314,
"children": {
"_process_rank_one_or_two_observation": {
"total": 72.392330554816,
"count": 511864,
"is_parallel": true,
"self": 72.392330554816
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 609.2261297620071,
"count": 63984,
"self": 2.42281830198408,
"children": {
"process_trajectory": {
"total": 118.23348753001574,
"count": 63984,
"self": 117.97695152901542,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25653600100031326,
"count": 2,
"self": 0.25653600100031326
}
}
},
"_update_policy": {
"total": 488.56982393000726,
"count": 457,
"self": 310.8689390789855,
"children": {
"TorchPPOOptimizer.update": {
"total": 177.70088485102178,
"count": 22764,
"self": 177.70088485102178
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0040002962341532e-06,
"count": 1,
"self": 1.0040002962341532e-06
},
"TrainerController._save_models": {
"total": 0.09030011999948329,
"count": 1,
"self": 0.0015473789999305154,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08875274099955277,
"count": 1,
"self": 0.08875274099955277
}
}
}
}
}
}
}