reneeshdenny's picture
First Push
f2f079d
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4646044671535492,
"min": 0.4375113248825073,
"max": 1.4169901609420776,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13878.6650390625,
"min": 13202.341796875,
"max": 42985.8125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989897.0,
"min": 29908.0,
"max": 989897.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989897.0,
"min": 29908.0,
"max": 989897.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4102872908115387,
"min": -0.0822429433465004,
"max": 0.479949951171875,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 111.18785858154297,
"min": -19.82054901123047,
"max": 129.10653686523438,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01453093346208334,
"min": -0.06011674925684929,
"max": 0.19163237512111664,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.937882900238037,
"min": -15.690471649169922,
"max": 46.18340301513672,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06770309856754206,
"min": 0.06389184295576776,
"max": 0.07401803335302422,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.015546478513131,
"min": 0.547246765904162,
"max": 1.0582341434589277,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014759760406979183,
"min": 0.0006078457775897352,
"max": 0.016211511451859097,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22139640610468775,
"min": 0.008509840886256293,
"max": 0.22696116032602734,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.523777492106664e-06,
"min": 7.523777492106664e-06,
"max": 0.0002947681142439625,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011285666238159996,
"min": 0.00011285666238159996,
"max": 0.0037588549470484,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250789333333334,
"min": 0.10250789333333334,
"max": 0.1982560375,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5376184,
"min": 1.4778355,
"max": 2.6529516000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026053854399999993,
"min": 0.00026053854399999993,
"max": 0.009825778146249999,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003908078159999999,
"min": 0.003908078159999999,
"max": 0.12530986484,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009656684473156929,
"min": 0.009569836780428886,
"max": 0.3550465404987335,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14485026895999908,
"min": 0.1339777112007141,
"max": 2.840372323989868,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 425.09722222222223,
"min": 380.7654320987654,
"max": 994.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30607.0,
"min": 17218.0,
"max": 32704.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.380405530333519,
"min": -0.9257862575609108,
"max": 1.5181555329925485,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 99.38919818401337,
"min": -28.364801704883575,
"max": 120.15639819204807,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.380405530333519,
"min": -0.9257862575609108,
"max": 1.5181555329925485,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 99.38919818401337,
"min": -28.364801704883575,
"max": 120.15639819204807,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0426171016701523,
"min": 0.03982504971881517,
"max": 7.23996159227358,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.0684313202509657,
"min": 2.9125236109248362,
"max": 130.31930866092443,
"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": "1698949304",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698951561"
},
"total": 2256.978047419,
"count": 1,
"self": 0.4770846729998084,
"children": {
"run_training.setup": {
"total": 0.06664318399998592,
"count": 1,
"self": 0.06664318399998592
},
"TrainerController.start_learning": {
"total": 2256.4343195620004,
"count": 1,
"self": 1.4463374480378661,
"children": {
"TrainerController._reset_env": {
"total": 3.829434703000061,
"count": 1,
"self": 3.829434703000061
},
"TrainerController.advance": {
"total": 2251.083995692962,
"count": 63631,
"self": 1.4869888418888877,
"children": {
"env_step": {
"total": 1628.4073629590491,
"count": 63631,
"self": 1495.9036279480301,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.63753388399778,
"count": 63631,
"self": 4.738194950046136,
"children": {
"TorchPolicy.evaluate": {
"total": 126.89933893395164,
"count": 62566,
"self": 126.89933893395164
}
}
},
"workers": {
"total": 0.8662011270212133,
"count": 63631,
"self": 0.0,
"children": {
"worker_root": {
"total": 2251.426877744984,
"count": 63631,
"is_parallel": true,
"self": 873.0935550349402,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002660341000023436,
"count": 1,
"is_parallel": true,
"self": 0.0007841999998845495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018761410001388867,
"count": 8,
"is_parallel": true,
"self": 0.0018761410001388867
}
}
},
"UnityEnvironment.step": {
"total": 0.048324933999992936,
"count": 1,
"is_parallel": true,
"self": 0.0005862319999323518,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004996449999907782,
"count": 1,
"is_parallel": true,
"self": 0.0004996449999907782
},
"communicator.exchange": {
"total": 0.04560871200010297,
"count": 1,
"is_parallel": true,
"self": 0.04560871200010297
},
"steps_from_proto": {
"total": 0.0016303449999668373,
"count": 1,
"is_parallel": true,
"self": 0.0003448439997555397,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012855010002112977,
"count": 8,
"is_parallel": true,
"self": 0.0012855010002112977
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1378.3333227100436,
"count": 63630,
"is_parallel": true,
"self": 34.670667690929804,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.09947040205111,
"count": 63630,
"is_parallel": true,
"self": 26.09947040205111
},
"communicator.exchange": {
"total": 1218.0638264540519,
"count": 63630,
"is_parallel": true,
"self": 1218.0638264540519
},
"steps_from_proto": {
"total": 99.49935816301081,
"count": 63630,
"is_parallel": true,
"self": 20.00295396607089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.49640419693992,
"count": 509040,
"is_parallel": true,
"self": 79.49640419693992
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 621.1896438920242,
"count": 63631,
"self": 2.7511197989754237,
"children": {
"process_trajectory": {
"total": 120.74321036505148,
"count": 63631,
"self": 120.58475561005184,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15845475499963868,
"count": 2,
"self": 0.15845475499963868
}
}
},
"_update_policy": {
"total": 497.69531372799725,
"count": 459,
"self": 297.8487905569839,
"children": {
"TorchPPOOptimizer.update": {
"total": 199.84652317101336,
"count": 22749,
"self": 199.84652317101336
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.499999578110874e-07,
"count": 1,
"self": 9.499999578110874e-07
},
"TrainerController._save_models": {
"total": 0.07455076800033567,
"count": 1,
"self": 0.001394175000314135,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07315659300002153,
"count": 1,
"self": 0.07315659300002153
}
}
}
}
}
}
}