ppo-pyramids / run_logs /timers.json
MerveOzer's picture
First Push
f7e35ad
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.4949517250061035,
"min": 1.4949517250061035,
"max": 1.4949517250061035,
"count": 1
},
"Pyramids.Policy.Entropy.sum": {
"value": 45350.85546875,
"min": 45350.85546875,
"max": 45350.85546875,
"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": 0.004319649655371904,
"min": 0.004319649655371904,
"max": 0.004319649655371904,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 1.023756980895996,
"min": 1.023756980895996,
"max": 1.023756980895996,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.2430337518453598,
"min": 0.2430337518453598,
"max": 0.2430337518453598,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 57.5989990234375,
"min": 57.5989990234375,
"max": 57.5989990234375,
"count": 1
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07270533144956226,
"min": 0.07270533144956226,
"max": 0.07270533144956226,
"count": 1
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.5089373201469358,
"min": 0.5089373201469358,
"max": 0.5089373201469358,
"count": 1
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.004417627666578346,
"min": 0.004417627666578346,
"max": 0.004417627666578346,
"count": 1
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.030923393666048418,
"min": 0.030923393666048418,
"max": 0.030923393666048418,
"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": 0.30819717049598694,
"min": 0.30819717049598694,
"max": 0.30819717049598694,
"count": 1
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 2.1573801040649414,
"min": 2.1573801040649414,
"max": 2.1573801040649414,
"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": 5.914294242858887,
"min": 5.914294242858887,
"max": 5.914294242858887,
"count": 1
},
"Pyramids.Policy.RndReward.sum": {
"value": 94.62870788574219,
"min": 94.62870788574219,
"max": 94.62870788574219,
"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": "1679073142",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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=FirstTraining --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": "1679073231"
},
"total": 88.67379218100001,
"count": 1,
"self": 0.5406468599999812,
"children": {
"run_training.setup": {
"total": 0.22062763500002802,
"count": 1,
"self": 0.22062763500002802
},
"TrainerController.start_learning": {
"total": 87.912517686,
"count": 1,
"self": 0.06306637699901785,
"children": {
"TrainerController._reset_env": {
"total": 7.1997608149999905,
"count": 1,
"self": 7.1997608149999905
},
"TrainerController.advance": {
"total": 80.53135972100097,
"count": 1896,
"self": 0.0677045579998321,
"children": {
"env_step": {
"total": 47.72100822900143,
"count": 1896,
"self": 43.51275766600122,
"children": {
"SubprocessEnvManager._take_step": {
"total": 4.16892672000057,
"count": 1896,
"self": 0.21829490300029875,
"children": {
"TorchPolicy.evaluate": {
"total": 3.9506318170002714,
"count": 1896,
"self": 3.9506318170002714
}
}
},
"workers": {
"total": 0.03932384299963587,
"count": 1896,
"self": 0.0,
"children": {
"worker_root": {
"total": 87.60746250199884,
"count": 1896,
"is_parallel": true,
"self": 49.430045904000224,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011890510000000631,
"count": 1,
"is_parallel": true,
"self": 0.006276446999947893,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005614063000052738,
"count": 8,
"is_parallel": true,
"self": 0.005614063000052738
}
}
},
"UnityEnvironment.step": {
"total": 0.060297167999976864,
"count": 1,
"is_parallel": true,
"self": 0.0006651850000025661,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004997460000026877,
"count": 1,
"is_parallel": true,
"self": 0.0004997460000026877
},
"communicator.exchange": {
"total": 0.05717189799997868,
"count": 1,
"is_parallel": true,
"self": 0.05717189799997868
},
"steps_from_proto": {
"total": 0.0019603389999929277,
"count": 1,
"is_parallel": true,
"self": 0.00045578200001727964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001504556999975648,
"count": 8,
"is_parallel": true,
"self": 0.001504556999975648
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 38.177416597998615,
"count": 1895,
"is_parallel": true,
"self": 1.298642941997457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.7496994060005591,
"count": 1895,
"is_parallel": true,
"self": 0.7496994060005591
},
"communicator.exchange": {
"total": 32.447079383999835,
"count": 1895,
"is_parallel": true,
"self": 32.447079383999835
},
"steps_from_proto": {
"total": 3.681994866000764,
"count": 1895,
"is_parallel": true,
"self": 0.8150765770022872,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.866918288998477,
"count": 15160,
"is_parallel": true,
"self": 2.866918288998477
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 32.74264693399971,
"count": 1896,
"self": 0.08585060900099961,
"children": {
"process_trajectory": {
"total": 4.350153718998627,
"count": 1896,
"self": 4.350153718998627
},
"_update_policy": {
"total": 28.306642606000082,
"count": 7,
"self": 11.82352638100042,
"children": {
"TorchPPOOptimizer.update": {
"total": 16.483116224999662,
"count": 663,
"self": 16.483116224999662
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1289999974906095e-06,
"count": 1,
"self": 1.1289999974906095e-06
},
"TrainerController._save_models": {
"total": 0.11832964400002766,
"count": 1,
"self": 0.0018249660000719814,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11650467799995567,
"count": 1,
"self": 0.11650467799995567
}
}
}
}
}
}
}