socks22's picture
first
1396607
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.4931830167770386,
"min": 1.4931830167770386,
"max": 1.4931830167770386,
"count": 1
},
"Pyramids.Policy.Entropy.sum": {
"value": 45297.19921875,
"min": 45297.19921875,
"max": 45297.19921875,
"count": 1
},
"Pyramids.Step.mean": {
"value": 29952.0,
"min": 29952.0,
"max": 29952.0,
"count": 1
},
"Pyramids.Step.sum": {
"value": 29952.0,
"min": 29952.0,
"max": 29952.0,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.14131538569927216,
"min": -0.14131538569927216,
"max": -0.14131538569927216,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -33.49174499511719,
"min": -33.49174499511719,
"max": -33.49174499511719,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.3937845528125763,
"min": 0.3937845528125763,
"max": 0.3937845528125763,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 93.32694244384766,
"min": 93.32694244384766,
"max": 93.32694244384766,
"count": 1
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07053563936598399,
"min": 0.07053563936598399,
"max": 0.07053563936598399,
"count": 1
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.4937494755618879,
"min": 0.4937494755618879,
"max": 0.4937494755618879,
"count": 1
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.006392476925940399,
"min": 0.006392476925940399,
"max": 0.006392476925940399,
"count": 1
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.04474733848158279,
"min": 0.04474733848158279,
"max": 0.04474733848158279,
"count": 1
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00013835433959619045,
"min": 0.00013835433959619045,
"max": 0.00013835433959619045,
"count": 1
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0009684803771733332,
"min": 0.0009684803771733332,
"max": 0.0009684803771733332,
"count": 1
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1461180952380953,
"min": 0.1461180952380953,
"max": 0.1461180952380953,
"count": 1
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.022826666666667,
"min": 1.022826666666667,
"max": 1.022826666666667,
"count": 1
},
"Pyramids.Policy.Beta.mean": {
"value": 0.004617197714285715,
"min": 0.004617197714285715,
"max": 0.004617197714285715,
"count": 1
},
"Pyramids.Policy.Beta.sum": {
"value": 0.032320384,
"min": 0.032320384,
"max": 0.032320384,
"count": 1
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.49464988708496094,
"min": 0.49464988708496094,
"max": 0.49464988708496094,
"count": 1
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 3.4625492095947266,
"min": 3.4625492095947266,
"max": 3.4625492095947266,
"count": 1
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 1
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 15984.0,
"min": 15984.0,
"max": 15984.0,
"count": 1
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 1
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -16.000000834465027,
"min": -16.000000834465027,
"max": -16.000000834465027,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -16.000000834465027,
"min": -16.000000834465027,
"max": -16.000000834465027,
"count": 1
},
"Pyramids.Policy.RndReward.mean": {
"value": 10.483762161806226,
"min": 10.483762161806226,
"max": 10.483762161806226,
"count": 1
},
"Pyramids.Policy.RndReward.sum": {
"value": 167.7401945888996,
"min": 167.7401945888996,
"max": 167.7401945888996,
"count": 1
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1704338972",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704339045"
},
"total": 72.46901897200007,
"count": 1,
"self": 0.5283092230000648,
"children": {
"run_training.setup": {
"total": 0.08451638700000785,
"count": 1,
"self": 0.08451638700000785
},
"TrainerController.start_learning": {
"total": 71.856193362,
"count": 1,
"self": 0.06713993199730339,
"children": {
"TrainerController._reset_env": {
"total": 2.487187332000076,
"count": 1,
"self": 2.487187332000076
},
"TrainerController.advance": {
"total": 69.16772260100254,
"count": 1896,
"self": 0.07196542000201589,
"children": {
"env_step": {
"total": 47.191943243002584,
"count": 1896,
"self": 41.275947654999186,
"children": {
"SubprocessEnvManager._take_step": {
"total": 5.877979689003496,
"count": 1896,
"self": 0.20323698400329704,
"children": {
"TorchPolicy.evaluate": {
"total": 5.674742705000199,
"count": 1896,
"self": 5.674742705000199
}
}
},
"workers": {
"total": 0.038015898999901765,
"count": 1896,
"self": 0.0,
"children": {
"worker_root": {
"total": 71.38978452500203,
"count": 1896,
"is_parallel": true,
"self": 34.90113670800349,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020455899999660687,
"count": 1,
"is_parallel": true,
"self": 0.0006460170000082144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013995729999578543,
"count": 8,
"is_parallel": true,
"self": 0.0013995729999578543
}
}
},
"UnityEnvironment.step": {
"total": 0.06339372100001128,
"count": 1,
"is_parallel": true,
"self": 0.0007008590000623371,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006034389999740597,
"count": 1,
"is_parallel": true,
"self": 0.0006034389999740597
},
"communicator.exchange": {
"total": 0.06005736999998135,
"count": 1,
"is_parallel": true,
"self": 0.06005736999998135
},
"steps_from_proto": {
"total": 0.002032052999993539,
"count": 1,
"is_parallel": true,
"self": 0.0004390290000628738,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001593023999930665,
"count": 8,
"is_parallel": true,
"self": 0.001593023999930665
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 36.48864781699854,
"count": 1895,
"is_parallel": true,
"self": 1.3414806269998962,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.9498945149993006,
"count": 1895,
"is_parallel": true,
"self": 0.9498945149993006
},
"communicator.exchange": {
"total": 30.292033882997544,
"count": 1895,
"is_parallel": true,
"self": 30.292033882997544
},
"steps_from_proto": {
"total": 3.9052387920017964,
"count": 1895,
"is_parallel": true,
"self": 0.8012820829977727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.1039567090040237,
"count": 15160,
"is_parallel": true,
"self": 3.1039567090040237
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 21.90381393799794,
"count": 1896,
"self": 0.07714586800045709,
"children": {
"process_trajectory": {
"total": 4.295150480997222,
"count": 1896,
"self": 4.295150480997222
},
"_update_policy": {
"total": 17.53151758900026,
"count": 7,
"self": 9.5916402010007,
"children": {
"TorchPPOOptimizer.update": {
"total": 7.939877387999559,
"count": 663,
"self": 7.939877387999559
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0670000847312622e-06,
"count": 1,
"self": 1.0670000847312622e-06
},
"TrainerController._save_models": {
"total": 0.13414242999999715,
"count": 1,
"self": 0.0017119569999977102,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13243047299999944,
"count": 1,
"self": 0.13243047299999944
}
}
}
}
}
}
}