ppo-Pyramids / run_logs /timers.json
bwilkie's picture
First Push
c0dbfa8
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.3937236070632935,
"min": 1.3937236070632935,
"max": 1.5890371799468994,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 69753.078125,
"min": 69709.3984375,
"max": 79528.1328125,
"count": 10
},
"Pyramids.Step.mean": {
"value": 499968.0,
"min": 49920.0,
"max": 499968.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 499968.0,
"min": 49920.0,
"max": 499968.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.09940119087696075,
"min": -0.09940119087696075,
"max": 0.06577372550964355,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -39.760475158691406,
"min": -39.760475158691406,
"max": 26.243717193603516,
"count": 10
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.02394913114425656,
"min": 0.021691647771424898,
"max": 0.028071414444400374,
"count": 10
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.09579652457702624,
"min": 0.08676659108569959,
"max": 0.11643507294744876,
"count": 10
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 3.9693593952037965e-05,
"min": 3.9693593952037965e-05,
"max": 0.0026047847794034903,
"count": 10
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.00015877437580815186,
"min": 0.00015877437580815186,
"max": 0.010419139117613961,
"count": 10
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.55136948288e-05,
"min": 1.55136948288e-05,
"max": 0.00028191360602879996,
"count": 10
},
"Pyramids.Policy.LearningRate.sum": {
"value": 6.20547793152e-05,
"min": 6.20547793152e-05,
"max": 0.0011276544241151998,
"count": 10
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10517120000000002,
"min": 0.10517120000000002,
"max": 0.1939712,
"count": 10
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.4206848000000001,
"min": 0.4206848000000001,
"max": 0.7758848,
"count": 10
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002680428800000001,
"min": 0.0002680428800000001,
"max": 0.004699162880000001,
"count": 10
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0010721715200000003,
"min": 0.0010721715200000003,
"max": 0.018796651520000002,
"count": 10
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 10
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 47952.0,
"min": 47952.0,
"max": 63936.0,
"count": 10
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 10
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -48.00000250339508,
"min": -63.00000328570604,
"max": -48.00000250339508,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -48.00000250339508,
"min": -63.00000328570604,
"max": -48.00000250339508,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1689786295",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --force --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689787308"
},
"total": 1013.613986283,
"count": 1,
"self": 0.536947930000224,
"children": {
"run_training.setup": {
"total": 0.03985256200007825,
"count": 1,
"self": 0.03985256200007825
},
"TrainerController.start_learning": {
"total": 1013.0371857909997,
"count": 1,
"self": 1.2283353200023157,
"children": {
"TrainerController._reset_env": {
"total": 1.4102321279999614,
"count": 1,
"self": 1.4102321279999614
},
"TrainerController.advance": {
"total": 1010.3314114759969,
"count": 31256,
"self": 1.1762683250083228,
"children": {
"env_step": {
"total": 764.154593203998,
"count": 31256,
"self": 707.2820088429914,
"children": {
"SubprocessEnvManager._take_step": {
"total": 56.16116271201349,
"count": 31256,
"self": 3.510930706048157,
"children": {
"TorchPolicy.evaluate": {
"total": 52.650232005965336,
"count": 31256,
"self": 52.650232005965336
}
}
},
"workers": {
"total": 0.7114216489931096,
"count": 31256,
"self": 0.0,
"children": {
"worker_root": {
"total": 1009.7733735070146,
"count": 31256,
"is_parallel": true,
"self": 385.3697634270302,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026957669999774225,
"count": 1,
"is_parallel": true,
"self": 0.0009450680004192691,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017506989995581534,
"count": 8,
"is_parallel": true,
"self": 0.0017506989995581534
}
}
},
"UnityEnvironment.step": {
"total": 0.059914064999929906,
"count": 1,
"is_parallel": true,
"self": 0.0007067689998621063,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006153689998882328,
"count": 1,
"is_parallel": true,
"self": 0.0006153689998882328
},
"communicator.exchange": {
"total": 0.05625404600004913,
"count": 1,
"is_parallel": true,
"self": 0.05625404600004913
},
"steps_from_proto": {
"total": 0.0023378810001304373,
"count": 1,
"is_parallel": true,
"self": 0.00042086400026164483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019170169998687925,
"count": 8,
"is_parallel": true,
"self": 0.0019170169998687925
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 624.4036100799844,
"count": 31255,
"is_parallel": true,
"self": 22.193880366982512,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.079053457035116,
"count": 31255,
"is_parallel": true,
"self": 12.079053457035116
},
"communicator.exchange": {
"total": 524.1716127559969,
"count": 31255,
"is_parallel": true,
"self": 524.1716127559969
},
"steps_from_proto": {
"total": 65.95906349996994,
"count": 31255,
"is_parallel": true,
"self": 14.176395434028791,
"children": {
"_process_rank_one_or_two_observation": {
"total": 51.78266806594115,
"count": 250040,
"is_parallel": true,
"self": 51.78266806594115
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 245.00054994699053,
"count": 31256,
"self": 1.3030557610077267,
"children": {
"process_trajectory": {
"total": 52.78492470198307,
"count": 31256,
"self": 52.64763206198313,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13729263999994146,
"count": 1,
"self": 0.13729263999994146
}
}
},
"_update_policy": {
"total": 190.91256948399973,
"count": 41,
"self": 147.90679110099722,
"children": {
"TorchPPOOptimizer.update": {
"total": 43.00577838300251,
"count": 1386,
"self": 43.00577838300251
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1040001481887884e-06,
"count": 1,
"self": 1.1040001481887884e-06
},
"TrainerController._save_models": {
"total": 0.06720576300040193,
"count": 1,
"self": 0.0006139710008028487,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06659179199959908,
"count": 1,
"self": 0.06659179199959908
}
}
}
}
}
}
}