Pumin1's picture
First push
54d2af4 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5138432383537292,
"min": 0.43701356649398804,
"max": 1.5415090322494507,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15415.296875,
"min": 12875.0234375,
"max": 46763.21875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989901.0,
"min": 29952.0,
"max": 989901.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989901.0,
"min": 29952.0,
"max": 989901.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.1627494990825653,
"min": -0.10430730879306793,
"max": 0.1779141128063202,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 41.501121520996094,
"min": -25.1380615234375,
"max": 44.65644073486328,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.022883247584104538,
"min": 0.01903068646788597,
"max": 0.49741992354393005,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.835227966308594,
"min": 4.700579643249512,
"max": 119.87820434570312,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.049042711024022925,
"min": 0.045422865313802116,
"max": 0.05224519318378015,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.3432989771681605,
"min": 0.2089807727351206,
"max": 0.41782850300660357,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012831757469289837,
"min": 0.0007189670630753296,
"max": 0.015707246094583144,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.08982230228502885,
"min": 0.005032769441527307,
"max": 0.09343702230762574,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 4.921068968085715e-06,
"min": 4.921068968085715e-06,
"max": 0.0001969664015168,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 3.4447482776600005e-05,
"min": 3.4447482776600005e-05,
"max": 0.0012540422729789003,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10123024285714285,
"min": 0.10123024285714285,
"max": 0.14924159999999997,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.7086117,
"min": 0.5969663999999999,
"max": 1.06196875,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00013277823714285714,
"min": 0.00013277823714285714,
"max": 0.00492431168,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0009294476600000001,
"min": 0.0009294476600000001,
"max": 0.031358352889999996,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01976649835705757,
"min": 0.01976649835705757,
"max": 0.8751938939094543,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1383654922246933,
"min": 0.1383654922246933,
"max": 3.5007755756378174,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 648.2291666666666,
"min": 616.2173913043479,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31115.0,
"min": 15984.0,
"max": 32796.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.8516291331810256,
"min": -1.0000000521540642,
"max": 0.9240511283278465,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 40.87819839268923,
"min": -30.51900166273117,
"max": 40.87819839268923,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.8516291331810256,
"min": -1.0000000521540642,
"max": 0.9240511283278465,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 40.87819839268923,
"min": -30.51900166273117,
"max": 40.87819839268923,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.13061968413785507,
"min": 0.1293959556509356,
"max": 17.11062474362552,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 6.269744838617044,
"min": 5.9522139599430375,
"max": 273.76999589800835,
"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": "1718798456",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718800638"
},
"total": 2182.24159227,
"count": 1,
"self": 0.4848205460002646,
"children": {
"run_training.setup": {
"total": 0.0513359550000132,
"count": 1,
"self": 0.0513359550000132
},
"TrainerController.start_learning": {
"total": 2181.705435769,
"count": 1,
"self": 1.4603605831025561,
"children": {
"TrainerController._reset_env": {
"total": 2.557083021999915,
"count": 1,
"self": 2.557083021999915
},
"TrainerController.advance": {
"total": 2177.630415218897,
"count": 63392,
"self": 1.4795215749009003,
"children": {
"env_step": {
"total": 1533.7528640039222,
"count": 63392,
"self": 1394.1321431029564,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.70787502693838,
"count": 63392,
"self": 4.877342726074403,
"children": {
"TorchPolicy.evaluate": {
"total": 133.83053230086398,
"count": 62575,
"self": 133.83053230086398
}
}
},
"workers": {
"total": 0.9128458740274255,
"count": 63392,
"self": 0.0,
"children": {
"worker_root": {
"total": 2176.568035039984,
"count": 63392,
"is_parallel": true,
"self": 911.4392693679338,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002088457999889215,
"count": 1,
"is_parallel": true,
"self": 0.0006344979997265909,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001453960000162624,
"count": 8,
"is_parallel": true,
"self": 0.001453960000162624
}
}
},
"UnityEnvironment.step": {
"total": 0.08411541699979352,
"count": 1,
"is_parallel": true,
"self": 0.0006435579994104046,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046319600005517714,
"count": 1,
"is_parallel": true,
"self": 0.00046319600005517714
},
"communicator.exchange": {
"total": 0.08123508300013782,
"count": 1,
"is_parallel": true,
"self": 0.08123508300013782
},
"steps_from_proto": {
"total": 0.0017735800001901225,
"count": 1,
"is_parallel": true,
"self": 0.0004067610002493893,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013668189999407332,
"count": 8,
"is_parallel": true,
"self": 0.0013668189999407332
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1265.1287656720501,
"count": 63391,
"is_parallel": true,
"self": 34.57319486889037,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.365751932084095,
"count": 63391,
"is_parallel": true,
"self": 24.365751932084095
},
"communicator.exchange": {
"total": 1104.765303514006,
"count": 63391,
"is_parallel": true,
"self": 1104.765303514006
},
"steps_from_proto": {
"total": 101.4245153570696,
"count": 63391,
"is_parallel": true,
"self": 20.902041923137404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.52247343393219,
"count": 507128,
"is_parallel": true,
"self": 80.52247343393219
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 642.3980296400737,
"count": 63392,
"self": 2.7367870171751747,
"children": {
"process_trajectory": {
"total": 130.20433362889526,
"count": 63392,
"self": 130.05660732489605,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14772630399920672,
"count": 2,
"self": 0.14772630399920672
}
}
},
"_update_policy": {
"total": 509.45690899400324,
"count": 233,
"self": 356.7710986229886,
"children": {
"TorchPPOOptimizer.update": {
"total": 152.68581037101467,
"count": 15304,
"self": 152.68581037101467
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.370005500386469e-07,
"count": 1,
"self": 9.370005500386469e-07
},
"TrainerController._save_models": {
"total": 0.05757600800006912,
"count": 1,
"self": 0.0008829930002320907,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05669301499983703,
"count": 1,
"self": 0.05669301499983703
}
}
}
}
}
}
}