{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43996867537498474, "min": 0.43996867537498474, "max": 1.464361310005188, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13297.61328125, "min": 13297.61328125, "max": 44422.86328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989947.0, "min": 29952.0, "max": 989947.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989947.0, "min": 29952.0, "max": 989947.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.510842502117157, "min": -0.1663544774055481, "max": 0.5240492820739746, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.94915771484375, "min": -39.42601013183594, "max": 142.01734924316406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02792303077876568, "min": -0.027294190600514412, "max": 0.5365931391716003, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.595064163208008, "min": -7.123783588409424, "max": 127.17257690429688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06965061186733577, "min": 0.06675326599652588, "max": 0.07480313703759951, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9751085661427009, "min": 0.5236219592631965, "max": 1.0489587763634822, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015148581526118607, "min": 0.0006815789612093381, "max": 0.016534995591953504, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2120801413656605, "min": 0.0074973685733027194, "max": 0.24802493387930255, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.549511769242855e-06, "min": 7.549511769242855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010569316476939997, "min": 0.00010569316476939997, "max": 0.0036345925884691994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251647142857144, "min": 0.10251647142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352306000000001, "min": 1.3886848, "max": 2.6115308, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026139549571428563, "min": 0.00026139549571428563, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003659536939999999, "min": 0.003659536939999999, "max": 0.12117192692, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01709519885480404, "min": 0.016437822952866554, "max": 0.4449348449707031, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23933279514312744, "min": 0.23012951016426086, "max": 3.114543914794922, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 381.925, "min": 350.04819277108436, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30554.0, "min": 15984.0, "max": 33302.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5680499836802482, "min": -1.0000000521540642, "max": 1.6017421509128018, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.44399869441986, "min": -31.998001664876938, "max": 132.94459852576256, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5680499836802482, "min": -1.0000000521540642, "max": 1.6017421509128018, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.44399869441986, "min": -31.998001664876938, "max": 132.94459852576256, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0675044783969497, "min": 0.06241423359680051, "max": 9.347806975245476, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.400358271755977, "min": 5.010137942968868, "max": 149.5649116039276, "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": "1786092081", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/content/mlagents-env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1786094475" }, "total": 2394.7761604470006, "count": 1, "self": 0.483365393000895, "children": { "run_training.setup": { "total": 0.019464259999949718, "count": 1, "self": 0.019464259999949718 }, "TrainerController.start_learning": { "total": 2394.273330794, "count": 1, "self": 1.3535576840858994, "children": { "TrainerController._reset_env": { "total": 2.1667872179996266, "count": 1, "self": 2.1667872179996266 }, "TrainerController.advance": { "total": 2390.673004841914, "count": 63773, "self": 1.404435554045449, "children": { "env_step": { "total": 1761.8269834410276, "count": 63773, "self": 1608.2928485290777, "children": { "SubprocessEnvManager._take_step": { "total": 152.71652088002702, "count": 63773, "self": 4.799261236938946, "children": { "TorchPolicy.evaluate": { "total": 147.91725964308807, "count": 62542, "self": 147.91725964308807 } } }, "workers": { "total": 0.817614031922858, "count": 63773, "self": 0.0, "children": { "worker_root": { "total": 2388.217843455999, "count": 63773, "is_parallel": true, "self": 898.6557827670222, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018501040003684466, "count": 1, "is_parallel": true, "self": 0.0006425320007110713, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012075719996573753, "count": 8, "is_parallel": true, "self": 0.0012075719996573753 } } }, "UnityEnvironment.step": { "total": 0.05062742699919909, "count": 1, "is_parallel": true, "self": 0.0005401659991548513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004947029992763419, "count": 1, "is_parallel": true, "self": 0.0004947029992763419 }, "communicator.exchange": { "total": 0.048024364999946556, "count": 1, "is_parallel": true, "self": 0.048024364999946556 }, "steps_from_proto": { "total": 0.0015681930008213385, "count": 1, "is_parallel": true, "self": 0.0003464560013526352, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012217369994687033, "count": 8, "is_parallel": true, "self": 0.0012217369994687033 } } } } } } }, "UnityEnvironment.step": { "total": 1489.562060688977, "count": 63772, "is_parallel": true, "self": 33.56976394170215, "children": { "UnityEnvironment._generate_step_input": { "total": 23.633580957056438, "count": 63772, "is_parallel": true, "self": 23.633580957056438 }, "communicator.exchange": { "total": 1322.3824957121233, "count": 63772, "is_parallel": true, "self": 1322.3824957121233 }, "steps_from_proto": { "total": 109.97622007809514, "count": 63772, "is_parallel": true, "self": 23.346019166345286, "children": { "_process_rank_one_or_two_observation": { "total": 86.63020091174985, "count": 510176, "is_parallel": true, "self": 86.63020091174985 } } } } } } } } } } }, "trainer_advance": { "total": 627.441585846841, "count": 63773, "self": 2.6458471637806724, "children": { "process_trajectory": { "total": 112.99712772905696, "count": 63773, "self": 112.81268242605711, "children": { "RLTrainer._checkpoint": { "total": 0.18444530299984763, "count": 2, "self": 0.18444530299984763 } } }, "_update_policy": { "total": 511.7986109540034, "count": 453, "self": 274.6977246809529, "children": { "TorchPPOOptimizer.update": { "total": 237.1008862730505, "count": 22791, "self": 237.1008862730505 } } } } } } }, "trainer_threads": { "total": 9.10000380827114e-07, "count": 1, "self": 9.10000380827114e-07 }, "TrainerController._save_models": { "total": 0.07998013999986142, "count": 1, "self": 0.0010033829994426924, "children": { "RLTrainer._checkpoint": { "total": 0.07897675700041873, "count": 1, "self": 0.07897675700041873 } } } } } } }