{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4446667432785034, "min": 0.44057270884513855, "max": 1.4400732517242432, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13169.25, "min": 13169.25, "max": 43686.0625, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4710139036178589, "min": -0.10547439008951187, "max": 0.5462679862976074, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.70274353027344, "min": -25.313854217529297, "max": 150.76995849609375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01824118383228779, "min": -0.02771620638668537, "max": 0.32963669300079346, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.906878471374512, "min": -7.649672985076904, "max": 79.77207946777344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06592705179909467, "min": 0.06592705179909467, "max": 0.07507849332312005, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9229787251873253, "min": 0.4898102235245711, "max": 1.0677037386146062, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015194363521351036, "min": 0.00043818245957129304, "max": 0.016107288791241414, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2127210892989145, "min": 0.00569637197442681, "max": 0.2255020430773798, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.337518982764283e-06, "min": 7.337518982764283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010272526575869996, "min": 0.00010272526575869996, "max": 0.0036332449889183993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244580714285714, "min": 0.10244580714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342413, "min": 1.3886848, "max": 2.6110816000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002543361335714285, "min": 0.0002543361335714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035607058699999995, "min": 0.0035607058699999995, "max": 0.12112705184, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008944369852542877, "min": 0.008873010985553265, "max": 0.44661977887153625, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12522117793560028, "min": 0.12522117793560028, "max": 3.126338481903076, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 396.5733333333333, "min": 350.71794871794873, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29743.0, "min": 15984.0, "max": 32821.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5233919805288314, "min": -1.0000000521540642, "max": 1.5976531447111806, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.25439853966236, "min": -29.90000158548355, "max": 127.06379841268063, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5233919805288314, "min": -1.0000000521540642, "max": 1.5976531447111806, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.25439853966236, "min": -29.90000158548355, "max": 127.06379841268063, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.036655700145832575, "min": 0.03358048028121054, "max": 8.496164211072028, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.749177510937443, "min": 2.6528579422156326, "max": 135.93862737715244, "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": "1763533041", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1763535247" }, "total": 2205.7953351470005, "count": 1, "self": 0.520360926000194, "children": { "run_training.setup": { "total": 0.019457908000276802, "count": 1, "self": 0.019457908000276802 }, "TrainerController.start_learning": { "total": 2205.255516313, "count": 1, "self": 1.3597876561084377, "children": { "TrainerController._reset_env": { "total": 1.6999940069999866, "count": 1, "self": 1.6999940069999866 }, "TrainerController.advance": { "total": 2202.1192347088913, "count": 63738, "self": 1.4632833071455025, "children": { "env_step": { "total": 1539.7103430378656, "count": 63738, "self": 1388.8011217909661, "children": { "SubprocessEnvManager._take_step": { "total": 150.0796850200013, "count": 63738, "self": 4.677773538021029, "children": { "TorchPolicy.evaluate": { "total": 145.40191148198028, "count": 62554, "self": 145.40191148198028 } } }, "workers": { "total": 0.829536226898199, "count": 63738, "self": 0.0, "children": { "worker_root": { "total": 2199.2502896630144, "count": 63738, "is_parallel": true, "self": 924.9192657910558, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019474300002002565, "count": 1, "is_parallel": true, "self": 0.0006064900003366347, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013409399998636218, "count": 8, "is_parallel": true, "self": 0.0013409399998636218 } } }, "UnityEnvironment.step": { "total": 0.05121618100019987, "count": 1, "is_parallel": true, "self": 0.0005424860000857734, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004582290002872469, "count": 1, "is_parallel": true, "self": 0.0004582290002872469 }, "communicator.exchange": { "total": 0.04858228800003417, "count": 1, "is_parallel": true, "self": 0.04858228800003417 }, "steps_from_proto": { "total": 0.0016331779997926787, "count": 1, "is_parallel": true, "self": 0.0003754280000975996, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012577499996950792, "count": 8, "is_parallel": true, "self": 0.0012577499996950792 } } } } } } }, "UnityEnvironment.step": { "total": 1274.3310238719587, "count": 63737, "is_parallel": true, "self": 33.233824390057634, "children": { "UnityEnvironment._generate_step_input": { "total": 23.936107232908853, "count": 63737, "is_parallel": true, "self": 23.936107232908853 }, "communicator.exchange": { "total": 1107.9236281920093, "count": 63737, "is_parallel": true, "self": 1107.9236281920093 }, "steps_from_proto": { "total": 109.23746405698284, "count": 63737, "is_parallel": true, "self": 23.076423102739227, "children": { "_process_rank_one_or_two_observation": { "total": 86.16104095424362, "count": 509896, "is_parallel": true, "self": 86.16104095424362 } } } } } } } } } } }, "trainer_advance": { "total": 660.9456083638802, "count": 63738, "self": 2.589653988844475, "children": { "process_trajectory": { "total": 124.69540458602023, "count": 63738, "self": 124.50883569202051, "children": { "RLTrainer._checkpoint": { "total": 0.18656889399971988, "count": 2, "self": 0.18656889399971988 } } }, "_update_policy": { "total": 533.6605497890155, "count": 454, "self": 300.29531344190355, "children": { "TorchPPOOptimizer.update": { "total": 233.36523634711193, "count": 22782, "self": 233.36523634711193 } } } } } } }, "trainer_threads": { "total": 1.0949997886200435e-06, "count": 1, "self": 1.0949997886200435e-06 }, "TrainerController._save_models": { "total": 0.07649884600050427, "count": 1, "self": 0.0010261080005875556, "children": { "RLTrainer._checkpoint": { "total": 0.07547273799991672, "count": 1, "self": 0.07547273799991672 } } } } } } }