ppo-Pyramids / run_logs /timers.json
cafernandez's picture
First Push
0305253 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.4956406354904175,
"min": 1.4956406354904175,
"max": 1.4956406354904175,
"count": 1
},
"Pyramids.Policy.Entropy.sum": {
"value": 45371.75390625,
"min": 45371.75390625,
"max": 45371.75390625,
"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": 0.08499304205179214,
"min": 0.08499304205179214,
"max": 0.08499304205179214,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 20.14335060119629,
"min": 20.14335060119629,
"max": 20.14335060119629,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.11598068475723267,
"min": 0.11598068475723267,
"max": 0.11598068475723267,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 27.487422943115234,
"min": 27.487422943115234,
"max": 27.487422943115234,
"count": 1
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06508968559293342,
"min": 0.06508968559293342,
"max": 0.06508968559293342,
"count": 1
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.455627799150534,
"min": 0.455627799150534,
"max": 0.455627799150534,
"count": 1
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005392135165601054,
"min": 0.005392135165601054,
"max": 0.005392135165601054,
"count": 1
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.03774494615920738,
"min": 0.03774494615920738,
"max": 0.03774494615920738,
"count": 1
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00013835433959619048,
"min": 0.00013835433959619048,
"max": 0.00013835433959619048,
"count": 1
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0009684803771733333,
"min": 0.0009684803771733333,
"max": 0.0009684803771733333,
"count": 1
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.14611809523809524,
"min": 0.14611809523809524,
"max": 0.14611809523809524,
"count": 1
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.0228266666666668,
"min": 1.0228266666666668,
"max": 1.0228266666666668,
"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": 0.49845558404922485,
"min": 0.49845558404922485,
"max": 0.49845558404922485,
"count": 1
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 3.4891891479492188,
"min": 3.4891891479492188,
"max": 3.4891891479492188,
"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": 9.056796200573444,
"min": 9.056796200573444,
"max": 9.056796200573444,
"count": 1
},
"Pyramids.Policy.RndReward.sum": {
"value": 144.9087392091751,
"min": 144.9087392091751,
"max": 144.9087392091751,
"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": "1728673922",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=PyramidsTraining2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728673974"
},
"total": 52.61547117800001,
"count": 1,
"self": 0.4763359139997192,
"children": {
"run_training.setup": {
"total": 0.051310552000359166,
"count": 1,
"self": 0.051310552000359166
},
"TrainerController.start_learning": {
"total": 52.08782471199993,
"count": 1,
"self": 0.03427276200363849,
"children": {
"TrainerController._reset_env": {
"total": 1.720803166999758,
"count": 1,
"self": 1.720803166999758
},
"TrainerController.advance": {
"total": 50.21873151899672,
"count": 1896,
"self": 0.036882062005133776,
"children": {
"env_step": {
"total": 32.96150874098748,
"count": 1896,
"self": 28.485718195019217,
"children": {
"SubprocessEnvManager._take_step": {
"total": 4.4532508999709535,
"count": 1896,
"self": 0.1315948199662671,
"children": {
"TorchPolicy.evaluate": {
"total": 4.321656080004686,
"count": 1896,
"self": 4.321656080004686
}
}
},
"workers": {
"total": 0.02253964599731262,
"count": 1896,
"self": 0.0,
"children": {
"worker_root": {
"total": 51.69474443197669,
"count": 1896,
"is_parallel": true,
"self": 26.35945445296693,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022034579997125547,
"count": 1,
"is_parallel": true,
"self": 0.0007618089994139154,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014416490002986393,
"count": 8,
"is_parallel": true,
"self": 0.0014416490002986393
}
}
},
"UnityEnvironment.step": {
"total": 0.04771484600041731,
"count": 1,
"is_parallel": true,
"self": 0.0006617349999942235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004542920005405904,
"count": 1,
"is_parallel": true,
"self": 0.0004542920005405904
},
"communicator.exchange": {
"total": 0.044799295000302664,
"count": 1,
"is_parallel": true,
"self": 0.044799295000302664
},
"steps_from_proto": {
"total": 0.0017995239995798329,
"count": 1,
"is_parallel": true,
"self": 0.0003969489998780773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014025749997017556,
"count": 8,
"is_parallel": true,
"self": 0.0014025749997017556
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 25.335289979009758,
"count": 1895,
"is_parallel": true,
"self": 0.9878521720474964,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.709960930973466,
"count": 1895,
"is_parallel": true,
"self": 0.709960930973466
},
"communicator.exchange": {
"total": 20.748114733991315,
"count": 1895,
"is_parallel": true,
"self": 20.748114733991315
},
"steps_from_proto": {
"total": 2.8893621419974806,
"count": 1895,
"is_parallel": true,
"self": 0.5886390349814974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.3007231070159833,
"count": 15160,
"is_parallel": true,
"self": 2.3007231070159833
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 17.220340716004102,
"count": 1896,
"self": 0.04507020999881206,
"children": {
"process_trajectory": {
"total": 3.938583631005713,
"count": 1896,
"self": 3.938583631005713
},
"_update_policy": {
"total": 13.236686874999577,
"count": 7,
"self": 6.991765996992399,
"children": {
"TorchPPOOptimizer.update": {
"total": 6.2449208780071785,
"count": 442,
"self": 6.2449208780071785
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2090004020137712e-06,
"count": 1,
"self": 1.2090004020137712e-06
},
"TrainerController._save_models": {
"total": 0.1140160549994107,
"count": 1,
"self": 0.0018649959993126686,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11215105900009803,
"count": 1,
"self": 0.11215105900009803
}
}
}
}
}
}
}