{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6112707853317261, "min": 0.6112707853317261, "max": 1.4750407934188843, "count": 32 }, "Pyramids.Policy.Entropy.sum": { "value": 18357.68359375, "min": 18357.68359375, "max": 44746.8359375, "count": 32 }, "Pyramids.Step.mean": { "value": 959965.0, "min": 29952.0, "max": 959965.0, "count": 32 }, "Pyramids.Step.sum": { "value": 959965.0, "min": 29952.0, "max": 959965.0, "count": 32 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40060266852378845, "min": -0.11375964432954788, "max": 0.40060266852378845, "count": 32 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 107.36151123046875, "min": -27.30231475830078, "max": 107.36151123046875, "count": 32 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004709061700850725, "min": -0.004709061700850725, "max": 0.36649659276008606, "count": 32 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.2620285749435425, "min": -1.2620285749435425, "max": 86.85969543457031, "count": 32 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.070701755425987, "min": 0.06639247318193103, "max": 0.07266993240206075, "count": 32 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.989824575963818, "min": 0.4768999761402682, "max": 1.065295705434241, "count": 32 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013848484154593844, "min": 0.0002759469205665732, "max": 0.013848484154593844, "count": 32 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19387877816431381, "min": 0.003311363046798879, "max": 0.19387877816431381, "count": 32 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002054573172285238, "min": 0.0002054573172285238, "max": 0.00029838354339596195, "count": 32 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0028764024411993333, "min": 0.0020886848037717336, "max": 0.0037591019469660667, "count": 32 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16848576190476192, "min": 0.16848576190476192, "max": 0.19946118095238097, "count": 32 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3588006666666668, "min": 1.3962282666666668, "max": 2.7374971666666674, "count": 32 }, "Pyramids.Policy.Beta.mean": { "value": 0.006851727614285715, "min": 0.006851727614285715, "max": 0.009946171977142856, "count": 32 }, "Pyramids.Policy.Beta.sum": { "value": 0.09592418660000002, "min": 0.06962320384, "max": 0.12531808994, "count": 32 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009787464514374733, "min": 0.009447549469769001, "max": 0.3883151113986969, "count": 32 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13702450692653656, "min": 0.13247673213481903, "max": 2.718205690383911, "count": 32 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 432.6056338028169, "min": 432.6056338028169, "max": 999.0, "count": 32 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30715.0, "min": 15984.0, "max": 32708.0, "count": 32 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3390056846397265, "min": -1.0000000521540642, "max": 1.3428475908816806, "count": 32 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.73039792478085, "min": -31.99640165269375, "max": 93.73039792478085, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3390056846397265, "min": -1.0000000521540642, "max": 1.3428475908816806, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.73039792478085, "min": -31.99640165269375, "max": 93.73039792478085, "count": 32 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043873532107266196, "min": 0.043873532107266196, "max": 7.543926483020186, "count": 32 }, "Pyramids.Policy.RndReward.sum": { "value": 3.071147247508634, "min": 2.8091354816569947, "max": 120.70282372832298, "count": 32 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 32 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704540326", "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": "1704542470" }, "total": 2143.926028734, "count": 1, "self": 0.4438866049999888, "children": { "run_training.setup": { "total": 0.06073886600006517, "count": 1, "self": 0.06073886600006517 }, "TrainerController.start_learning": { "total": 2143.421403263, "count": 1, "self": 1.4575312379720344, "children": { "TrainerController._reset_env": { "total": 3.246897249999961, "count": 1, "self": 3.246897249999961 }, "TrainerController.advance": { "total": 2138.5793076880277, "count": 60783, "self": 1.5545716399660705, "children": { "env_step": { "total": 1505.7944291930323, "count": 60783, "self": 1366.4909689750407, "children": { "SubprocessEnvManager._take_step": { "total": 138.39445156898114, "count": 60783, "self": 4.910825323039035, "children": { "TorchPolicy.evaluate": { "total": 133.4836262459421, "count": 60080, "self": 133.4836262459421 } } }, "workers": { "total": 0.909008649010616, "count": 60782, "self": 0.0, "children": { "worker_root": { "total": 2137.913850550014, "count": 60782, "is_parallel": true, "self": 897.0945458040335, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005366925999965133, "count": 1, "is_parallel": true, "self": 0.004099639999708415, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012672860002567177, "count": 8, "is_parallel": true, "self": 0.0012672860002567177 } } }, "UnityEnvironment.step": { "total": 0.05468615300003421, "count": 1, "is_parallel": true, "self": 0.0006977869999218456, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005491900000151873, "count": 1, "is_parallel": true, "self": 0.0005491900000151873 }, "communicator.exchange": { "total": 0.05154506799999581, "count": 1, "is_parallel": true, "self": 0.05154506799999581 }, "steps_from_proto": { "total": 0.0018941080001013688, "count": 1, "is_parallel": true, "self": 0.000491407000140498, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014027009999608708, "count": 8, "is_parallel": true, "self": 0.0014027009999608708 } } } } } } }, "UnityEnvironment.step": { "total": 1240.8193047459806, "count": 60781, "is_parallel": true, "self": 35.99210646997585, "children": { "UnityEnvironment._generate_step_input": { "total": 26.61474424299172, "count": 60781, "is_parallel": true, "self": 26.61474424299172 }, "communicator.exchange": { "total": 1072.3886338720013, "count": 60781, "is_parallel": true, "self": 1072.3886338720013 }, "steps_from_proto": { "total": 105.82382016101167, "count": 60781, "is_parallel": true, "self": 21.707789416840228, "children": { "_process_rank_one_or_two_observation": { "total": 84.11603074417144, "count": 486248, "is_parallel": true, "self": 84.11603074417144 } } } } } } } } } } }, "trainer_advance": { "total": 631.2303068550295, "count": 60782, "self": 2.7163348750676732, "children": { "process_trajectory": { "total": 129.54482761396423, "count": 60782, "self": 129.43830833996424, "children": { "RLTrainer._checkpoint": { "total": 0.10651927399999295, "count": 1, "self": 0.10651927399999295 } } }, "_update_policy": { "total": 498.96914436599764, "count": 420, "self": 296.2691013579931, "children": { "TorchPPOOptimizer.update": { "total": 202.7000430080045, "count": 21924, "self": 202.7000430080045 } } } } } } }, "trainer_threads": { "total": 1.3700000636163168e-06, "count": 1, "self": 1.3700000636163168e-06 }, "TrainerController._save_models": { "total": 0.13766571699989072, "count": 1, "self": 0.0020739960000355495, "children": { "RLTrainer._checkpoint": { "total": 0.13559172099985517, "count": 1, "self": 0.13559172099985517 } } } } } } }