andriJulian's picture
First Push
9d91d6b verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4915878474712372,
"min": 0.4915878474712372,
"max": 1.1058815717697144,
"count": 20
},
"Pyramids.Policy.Entropy.sum": {
"value": 24610.853515625,
"min": 24610.853515625,
"max": 55347.16015625,
"count": 20
},
"Pyramids.Step.mean": {
"value": 999950.0,
"min": 49920.0,
"max": 999950.0,
"count": 20
},
"Pyramids.Step.sum": {
"value": 999950.0,
"min": 49920.0,
"max": 999950.0,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3956849277019501,
"min": -0.10895395278930664,
"max": 0.40635430812835693,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 175.28842163085938,
"min": -43.581581115722656,
"max": 180.4213104248047,
"count": 20
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0075963144190609455,
"min": -0.1109791174530983,
"max": 0.495175302028656,
"count": 20
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -3.3651673793792725,
"min": -47.832000732421875,
"max": 197.574951171875,
"count": 20
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06771851495033976,
"min": 0.06646999074430746,
"max": 0.07199637223229345,
"count": 20
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.5575258438578146,
"min": 0.855752484895016,
"max": 1.720558527794863,
"count": 20
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014777340576289268,
"min": 0.0001917751803366107,
"max": 0.014777340576289268,
"count": 20
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.3398788332546532,
"min": 0.004219053967405436,
"max": 0.35214315212215297,
"count": 20
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.465219250756523e-06,
"min": 7.465219250756523e-06,
"max": 0.00029215680261440003,
"count": 20
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00017170004276740003,
"min": 0.00017170004276740003,
"max": 0.005119725493425,
"count": 20
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248837391304351,
"min": 0.10248837391304351,
"max": 0.19738560000000002,
"count": 20
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.3572326000000006,
"min": 2.3110272,
"max": 3.9675193,
"count": 20
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025858855391304355,
"min": 0.00025858855391304355,
"max": 0.00973882144,
"count": 20
},
"Pyramids.Policy.Beta.sum": {
"value": 0.005947536740000001,
"min": 0.005947536740000001,
"max": 0.17070684249999998,
"count": 20
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0175373163074255,
"min": 0.017334356904029846,
"max": 0.45273861289024353,
"count": 20
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.4033582806587219,
"min": 0.4033582806587219,
"max": 5.432863235473633,
"count": 20
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 447.6818181818182,
"min": 440.495652173913,
"max": 999.0,
"count": 20
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 49245.0,
"min": 46429.0,
"max": 52718.0,
"count": 20
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4250072499567812,
"min": -1.0000000521540642,
"max": 1.4250072499567812,
"count": 20
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 156.75079749524593,
"min": -48.00000250339508,
"max": 156.75079749524593,
"count": 20
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4250072499567812,
"min": -1.0000000521540642,
"max": 1.4250072499567812,
"count": 20
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 156.75079749524593,
"min": -48.00000250339508,
"max": 156.75079749524593,
"count": 20
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08055701851507448,
"min": 0.07907373148482293,
"max": 6.218042069580406,
"count": 20
},
"Pyramids.Policy.RndReward.sum": {
"value": 8.861272036658193,
"min": 8.861272036658193,
"max": 298.4660193398595,
"count": 20
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1722224275",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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 Training1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722226335"
},
"total": 2059.490229813,
"count": 1,
"self": 0.48992231000056563,
"children": {
"run_training.setup": {
"total": 0.05243329099994298,
"count": 1,
"self": 0.05243329099994298
},
"TrainerController.start_learning": {
"total": 2058.9478742119995,
"count": 1,
"self": 1.2112146869758362,
"children": {
"TrainerController._reset_env": {
"total": 2.0327732300002026,
"count": 1,
"self": 2.0327732300002026
},
"TrainerController.advance": {
"total": 2055.6234845790236,
"count": 63461,
"self": 1.3826268219168014,
"children": {
"env_step": {
"total": 1441.7784067311836,
"count": 63461,
"self": 1318.2802714901322,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.75354537095063,
"count": 63461,
"self": 4.499134926008992,
"children": {
"TorchPolicy.evaluate": {
"total": 118.25441044494164,
"count": 62573,
"self": 118.25441044494164
}
}
},
"workers": {
"total": 0.7445898701007536,
"count": 63461,
"self": 0.0,
"children": {
"worker_root": {
"total": 2054.127055583976,
"count": 63461,
"is_parallel": true,
"self": 850.688055591942,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002312417000212008,
"count": 1,
"is_parallel": true,
"self": 0.00072467400059395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001587742999618058,
"count": 8,
"is_parallel": true,
"self": 0.001587742999618058
}
}
},
"UnityEnvironment.step": {
"total": 0.04698383899994951,
"count": 1,
"is_parallel": true,
"self": 0.0006456720002461225,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004434140000739717,
"count": 1,
"is_parallel": true,
"self": 0.0004434140000739717
},
"communicator.exchange": {
"total": 0.04423475699968549,
"count": 1,
"is_parallel": true,
"self": 0.04423475699968549
},
"steps_from_proto": {
"total": 0.0016599959999439307,
"count": 1,
"is_parallel": true,
"self": 0.0003750760001821618,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012849199997617688,
"count": 8,
"is_parallel": true,
"self": 0.0012849199997617688
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1203.438999992034,
"count": 63460,
"is_parallel": true,
"self": 32.54583696921736,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.664057235911514,
"count": 63460,
"is_parallel": true,
"self": 22.664057235911514
},
"communicator.exchange": {
"total": 1052.810512043981,
"count": 63460,
"is_parallel": true,
"self": 1052.810512043981
},
"steps_from_proto": {
"total": 95.41859374292426,
"count": 63460,
"is_parallel": true,
"self": 19.065474460133373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.35311928279089,
"count": 507680,
"is_parallel": true,
"self": 76.35311928279089
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 612.4624510259232,
"count": 63461,
"self": 2.2458697658858,
"children": {
"process_trajectory": {
"total": 124.26756903803562,
"count": 63461,
"self": 124.0679947000358,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19957433799982027,
"count": 2,
"self": 0.19957433799982027
}
}
},
"_update_policy": {
"total": 485.9490122220018,
"count": 435,
"self": 287.2463275340051,
"children": {
"TorchPPOOptimizer.update": {
"total": 198.70268468799668,
"count": 22830,
"self": 198.70268468799668
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.22000253922306e-07,
"count": 1,
"self": 9.22000253922306e-07
},
"TrainerController._save_models": {
"total": 0.08040079399961542,
"count": 1,
"self": 0.001391196999065869,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07900959700054955,
"count": 1,
"self": 0.07900959700054955
}
}
}
}
}
}
}