ppo-pyramid / run_logs /timers.json
torkable's picture
v3 push
703832d verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5243778228759766,
"min": 0.5243778228759766,
"max": 1.5875117778778076,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15949.4765625,
"min": 15949.4765625,
"max": 50800.375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989991.0,
"min": 29912.0,
"max": 989991.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989991.0,
"min": 29912.0,
"max": 989991.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7561801671981812,
"min": -0.07969450950622559,
"max": 0.7615589499473572,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 134.60006713867188,
"min": -9.643035888671875,
"max": 134.60006713867188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.06732966750860214,
"min": 0.05978873744606972,
"max": 0.3954293727874756,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 11.98468017578125,
"min": 9.223644256591797,
"max": 47.056095123291016,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.263246567757945,
"min": 0.162251219440653,
"max": 0.28064506884591905,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.842725974305615,
"min": 0.5957608687555572,
"max": 2.385550743019849,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01390050204017647,
"min": 0.0007481948838782652,
"max": 0.02576252957805991,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.09730351428123529,
"min": 0.0029927795355130606,
"max": 0.14672159546656377,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 4.924011823757149e-06,
"min": 4.924011823757149e-06,
"max": 0.00019677440161280002,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 3.446808276630004e-05,
"min": 3.446808276630004e-05,
"max": 0.0012878945560528,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10246195714285715,
"min": 0.10246195714285715,
"max": 0.19838719999999999,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.7172337000000001,
"min": 0.5951616,
"max": 1.4439472000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0005021452328571434,
"min": 0.0005021452328571434,
"max": 0.019677601280000002,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035150166300000037,
"min": 0.0035150166300000037,
"max": 0.12880504528,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.017609162256121635,
"min": 0.017609162256121635,
"max": 0.4725158214569092,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1232641413807869,
"min": 0.1232641413807869,
"max": 1.4175474643707275,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 252.51260504201682,
"min": 252.1900826446281,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30049.0,
"min": 15984.0,
"max": 32881.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7130554471196247,
"min": -1.0000000596046448,
"max": 1.7238383612247428,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 203.85359820723534,
"min": -32.00000190734863,
"max": 205.43919748067856,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7130554471196247,
"min": -1.0000000596046448,
"max": 1.7238383612247428,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 203.85359820723534,
"min": -32.00000190734863,
"max": 205.43919748067856,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.1013398526614031,
"min": 0.1013398526614031,
"max": 14.708561448947243,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 12.059442466706969,
"min": 12.059442466706969,
"max": 338.2969133257866,
"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": "1736909271",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 v3 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736910888"
},
"total": 1617.421274761,
"count": 1,
"self": 0.3222304789996997,
"children": {
"run_training.setup": {
"total": 0.05562955799905467,
"count": 1,
"self": 0.05562955799905467
},
"TrainerController.start_learning": {
"total": 1617.0434147240012,
"count": 1,
"self": 1.432687056474606,
"children": {
"TrainerController._reset_env": {
"total": 2.213019042999804,
"count": 1,
"self": 2.213019042999804
},
"TrainerController.advance": {
"total": 1613.184121873528,
"count": 64476,
"self": 1.391465668750243,
"children": {
"env_step": {
"total": 1151.9368688379436,
"count": 64476,
"self": 947.7798050548936,
"children": {
"SubprocessEnvManager._take_step": {
"total": 203.31933904584912,
"count": 64476,
"self": 5.6842080557999,
"children": {
"TorchPolicy.evaluate": {
"total": 197.63513099004922,
"count": 62604,
"self": 197.63513099004922
}
}
},
"workers": {
"total": 0.8377247372009151,
"count": 64476,
"self": 0.0,
"children": {
"worker_root": {
"total": 1614.539795079083,
"count": 64476,
"is_parallel": true,
"self": 768.8650052684297,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021216360000835266,
"count": 1,
"is_parallel": true,
"self": 0.0007025060040177777,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014191299960657489,
"count": 8,
"is_parallel": true,
"self": 0.0014191299960657489
}
}
},
"UnityEnvironment.step": {
"total": 0.036326646000816254,
"count": 1,
"is_parallel": true,
"self": 0.000447165000878158,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029942999935883563,
"count": 1,
"is_parallel": true,
"self": 0.00029942999935883563
},
"communicator.exchange": {
"total": 0.034404144000291126,
"count": 1,
"is_parallel": true,
"self": 0.034404144000291126
},
"steps_from_proto": {
"total": 0.0011759070002881344,
"count": 1,
"is_parallel": true,
"self": 0.0002542710008128779,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009216359994752565,
"count": 8,
"is_parallel": true,
"self": 0.0009216359994752565
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 845.6747898106532,
"count": 64475,
"is_parallel": true,
"self": 22.17403085114529,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.508953462684076,
"count": 64475,
"is_parallel": true,
"self": 14.508953462684076
},
"communicator.exchange": {
"total": 744.292538688991,
"count": 64475,
"is_parallel": true,
"self": 744.292538688991
},
"steps_from_proto": {
"total": 64.69926680783283,
"count": 64475,
"is_parallel": true,
"self": 13.945041000521087,
"children": {
"_process_rank_one_or_two_observation": {
"total": 50.75422580731174,
"count": 515800,
"is_parallel": true,
"self": 50.75422580731174
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 459.8557873668342,
"count": 64476,
"self": 3.0521678690147382,
"children": {
"process_trajectory": {
"total": 184.29631291984515,
"count": 64476,
"self": 183.84416709984544,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45214581999971415,
"count": 2,
"self": 0.45214581999971415
}
}
},
"_update_policy": {
"total": 272.5073065779743,
"count": 239,
"self": 86.36038117900716,
"children": {
"TorchPPOOptimizer.update": {
"total": 186.14692539896714,
"count": 12339,
"self": 186.14692539896714
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.894999852287583e-06,
"count": 1,
"self": 2.894999852287583e-06
},
"TrainerController._save_models": {
"total": 0.21358385599887697,
"count": 1,
"self": 0.0027262570001767017,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21085759899870027,
"count": 1,
"self": 0.21085759899870027
}
}
}
}
}
}
}