ppo-PyramidsRND / run_logs /timers.json
Qilex's picture
first try
12ae4ac
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.32218632102012634,
"min": 0.32218632102012634,
"max": 1.417680025100708,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9598.5751953125,
"min": 9598.5751953125,
"max": 43006.7421875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989967.0,
"min": 29925.0,
"max": 989967.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989967.0,
"min": 29925.0,
"max": 989967.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.48654529452323914,
"min": -0.10096907615661621,
"max": 0.6211122274398804,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 133.79995727539062,
"min": -24.253517150878906,
"max": 174.53253173828125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.023541927337646484,
"min": -0.0011328005930408835,
"max": 0.3510272204875946,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.474030017852783,
"min": -0.29792654514312744,
"max": 83.19345092773438,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0695969604644781,
"min": 0.06443182451363802,
"max": 0.07345597657314058,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9743574465026933,
"min": 0.4958543585895711,
"max": 1.0447592619953758,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016993682267506614,
"min": 0.000713795746494557,
"max": 0.017529804446981177,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23791155174509257,
"min": 0.007851753211440127,
"max": 0.2454172622577365,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.638976025135713e-06,
"min": 7.638976025135713e-06,
"max": 0.0002952340730172143,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010694566435189998,
"min": 0.00010694566435189998,
"max": 0.0032548496150501998,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254629285714287,
"min": 0.10254629285714287,
"max": 0.19841135714285715,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4356481,
"min": 1.3888795,
"max": 2.4826161,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026437465642857144,
"min": 0.00026437465642857144,
"max": 0.009841294578571427,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037012451900000003,
"min": 0.0037012451900000003,
"max": 0.10851648502,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.016000542789697647,
"min": 0.016000542789697647,
"max": 0.4562482237815857,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.22400760650634766,
"min": 0.22400760650634766,
"max": 3.193737506866455,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 344.3370786516854,
"min": 323.82022471910113,
"max": 996.5806451612904,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30646.0,
"min": 16596.0,
"max": 32642.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5855636105618693,
"min": -0.9330065036492963,
"max": 1.6537011029680124,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 139.5295977294445,
"min": -30.626201704144478,
"max": 147.1793981641531,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5855636105618693,
"min": -0.9330065036492963,
"max": 1.6537011029680124,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 139.5295977294445,
"min": -30.626201704144478,
"max": 147.1793981641531,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05686455532552579,
"min": 0.05686455532552579,
"max": 8.655580476802939,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.00408086864627,
"min": 5.00408086864627,
"max": 147.14486810564995,
"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": "1674132593",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674134692"
},
"total": 2099.230538492,
"count": 1,
"self": 0.4243024410002363,
"children": {
"run_training.setup": {
"total": 0.10984147299996039,
"count": 1,
"self": 0.10984147299996039
},
"TrainerController.start_learning": {
"total": 2098.696394578,
"count": 1,
"self": 1.2625659520158479,
"children": {
"TrainerController._reset_env": {
"total": 6.117145030000074,
"count": 1,
"self": 6.117145030000074
},
"TrainerController.advance": {
"total": 2091.2296980779834,
"count": 63912,
"self": 1.2819954649921783,
"children": {
"env_step": {
"total": 1425.4749036940316,
"count": 63912,
"self": 1317.3880180700214,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.26816299203801,
"count": 63912,
"self": 4.4487346080372845,
"children": {
"TorchPolicy.evaluate": {
"total": 102.81942838400073,
"count": 62561,
"self": 34.71087786992098,
"children": {
"TorchPolicy.sample_actions": {
"total": 68.10855051407975,
"count": 62561,
"self": 68.10855051407975
}
}
}
}
},
"workers": {
"total": 0.8187226319721503,
"count": 63912,
"self": 0.0,
"children": {
"worker_root": {
"total": 2093.959562874037,
"count": 63912,
"is_parallel": true,
"self": 879.2294356219936,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017212289999406494,
"count": 1,
"is_parallel": true,
"self": 0.0006590159998722811,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010622130000683683,
"count": 8,
"is_parallel": true,
"self": 0.0010622130000683683
}
}
},
"UnityEnvironment.step": {
"total": 0.04934523400015678,
"count": 1,
"is_parallel": true,
"self": 0.0005252009998457652,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044360000015331025,
"count": 1,
"is_parallel": true,
"self": 0.00044360000015331025
},
"communicator.exchange": {
"total": 0.04644157699999596,
"count": 1,
"is_parallel": true,
"self": 0.04644157699999596
},
"steps_from_proto": {
"total": 0.0019348560001617443,
"count": 1,
"is_parallel": true,
"self": 0.00044470200009527616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014901540000664681,
"count": 8,
"is_parallel": true,
"self": 0.0014901540000664681
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1214.7301272520435,
"count": 63911,
"is_parallel": true,
"self": 28.141131763056592,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.962738398002784,
"count": 63911,
"is_parallel": true,
"self": 23.962738398002784
},
"communicator.exchange": {
"total": 1058.0187053659834,
"count": 63911,
"is_parallel": true,
"self": 1058.0187053659834
},
"steps_from_proto": {
"total": 104.6075517250008,
"count": 63911,
"is_parallel": true,
"self": 23.2369245229263,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.3706272020745,
"count": 511288,
"is_parallel": true,
"self": 81.3706272020745
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 664.4727989189596,
"count": 63912,
"self": 2.3066455699427024,
"children": {
"process_trajectory": {
"total": 148.80680335001898,
"count": 63912,
"self": 148.6195796840184,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18722366600059104,
"count": 2,
"self": 0.18722366600059104
}
}
},
"_update_policy": {
"total": 513.3593499989979,
"count": 448,
"self": 197.59070913301753,
"children": {
"TorchPPOOptimizer.update": {
"total": 315.7686408659804,
"count": 22818,
"self": 315.7686408659804
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.890000001178123e-07,
"count": 1,
"self": 9.890000001178123e-07
},
"TrainerController._save_models": {
"total": 0.08698452900034681,
"count": 1,
"self": 0.0012948880003023078,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0856896410000445,
"count": 1,
"self": 0.0856896410000445
}
}
}
}
}
}
}