{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5120686888694763, "min": 0.5120686888694763, "max": 1.408711552619934, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15230.970703125, "min": 15230.970703125, "max": 36559.98828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989938.0, "min": 29952.0, "max": 989938.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989938.0, "min": 29952.0, "max": 989938.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4751848578453064, "min": -0.11591996997594833, "max": 0.5172623991966248, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 130.20065307617188, "min": -27.453330993652344, "max": 141.21263122558594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0240505151450634, "min": -0.004350823815912008, "max": 0.6474699378013611, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.589841365814209, "min": -1.1051092147827148, "max": 93.45059204101562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06936893386453101, "min": 0.06559884865639122, "max": 0.07331581064176539, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9711650741034341, "min": 0.21994743192529614, "max": 1.037022718522862, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0133743752234122, "min": 0.00013020616660706534, "max": 0.015697891011465497, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1872412531277708, "min": 0.0018228863324989148, "max": 0.2263555836252635, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.57794747405e-06, "min": 7.57794747405e-06, "max": 0.00029274240241920004, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001060912646367, "min": 0.0001060912646367, "max": 0.0035071304309565996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252595, "min": 0.10252595, "max": 0.19758080000000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353633000000001, "min": 0.5927424000000001, "max": 2.5690434, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000262342405, "min": 0.000262342405, "max": 0.00975832192, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00367279367, "min": 0.00367279367, "max": 0.11692743566, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01436797808855772, "min": 0.01436797808855772, "max": 0.3530772626399994, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20115169882774353, "min": 0.20115169882774353, "max": 1.9913368225097656, "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 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 385.6623376623377, "min": 364.07142857142856, "max": 999.0, "count": 32 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29696.0, "min": 23043.0, "max": 33545.0, "count": 32 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5623740092306941, "min": -0.9999125525355339, "max": 1.6121095030435495, "count": 32 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.30279871076345, "min": -31.997201681137085, "max": 135.41719825565815, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5623740092306941, "min": -0.9999125525355339, "max": 1.6121095030435495, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.30279871076345, "min": -31.997201681137085, "max": 135.41719825565815, "count": 32 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05785227258995481, "min": 0.05721240604561033, "max": 3.2339698122814298, "count": 32 }, "Pyramids.Policy.RndReward.sum": { "value": 4.45462498942652, "min": 4.45462498942652, "max": 103.48703399300575, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1781877041", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [GCC 11.2.0]", "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 --resume", "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": "1781879252" }, "total": 2211.2940066749998, "count": 1, "self": 0.8005908999994062, "children": { "run_training.setup": { "total": 0.024940361000062694, "count": 1, "self": 0.024940361000062694 }, "TrainerController.start_learning": { "total": 2210.4684754140003, "count": 1, "self": 1.4096679800168204, "children": { "TrainerController._reset_env": { "total": 2.217420940000011, "count": 1, "self": 2.217420940000011 }, "TrainerController.advance": { "total": 2206.7527264819832, "count": 62566, "self": 1.3806673869476072, "children": { "env_step": { "total": 1585.3235300690199, "count": 62566, "self": 1430.9998073929937, "children": { "SubprocessEnvManager._take_step": { "total": 153.49355931602577, "count": 62566, "self": 4.655596836030327, "children": { "TorchPolicy.evaluate": { "total": 148.83796247999544, "count": 61574, "self": 148.83796247999544 } } }, "workers": { "total": 0.8301633600003697, "count": 62566, "self": 0.0, "children": { "worker_root": { "total": 2205.0027601590673, "count": 62566, "is_parallel": true, "self": 890.0210931561228, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00199788100007936, "count": 1, "is_parallel": true, "self": 0.0006497859999399225, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013480950001394376, "count": 8, "is_parallel": true, "self": 0.0013480950001394376 } } }, "UnityEnvironment.step": { "total": 0.05119965599988063, "count": 1, "is_parallel": true, "self": 0.0005992839996906696, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004449699999895529, "count": 1, "is_parallel": true, "self": 0.0004449699999895529 }, "communicator.exchange": { "total": 0.0485239790000378, "count": 1, "is_parallel": true, "self": 0.0485239790000378 }, "steps_from_proto": { "total": 0.0016314230001626129, "count": 1, "is_parallel": true, "self": 0.0003558959997462807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012755270004163322, "count": 8, "is_parallel": true, "self": 0.0012755270004163322 } } } } } } }, "UnityEnvironment.step": { "total": 1314.9816670029445, "count": 62565, "is_parallel": true, "self": 33.69531193177181, "children": { "UnityEnvironment._generate_step_input": { "total": 22.909965183055192, "count": 62565, "is_parallel": true, "self": 22.909965183055192 }, "communicator.exchange": { "total": 1150.7796662280616, "count": 62565, "is_parallel": true, "self": 1150.7796662280616 }, "steps_from_proto": { "total": 107.59672366005589, "count": 62565, "is_parallel": true, "self": 22.121438285010754, "children": { "_process_rank_one_or_two_observation": { "total": 85.47528537504513, "count": 500520, "is_parallel": true, "self": 85.47528537504513 } } } } } } } } } } }, "trainer_advance": { "total": 620.0485290260158, "count": 62566, "self": 2.657449789991915, "children": { "process_trajectory": { "total": 109.28301224503048, "count": 62566, "self": 109.09334325903001, "children": { "RLTrainer._checkpoint": { "total": 0.18966898600046989, "count": 2, "self": 0.18966898600046989 } } }, "_update_policy": { "total": 508.1080669909934, "count": 446, "self": 269.5641773779539, "children": { "TorchPPOOptimizer.update": { "total": 238.54388961303948, "count": 22428, "self": 238.54388961303948 } } } } } } }, "trainer_threads": { "total": 9.830000635702163e-07, "count": 1, "self": 9.830000635702163e-07 }, "TrainerController._save_models": { "total": 0.08865902900015499, "count": 1, "self": 0.002643509000336053, "children": { "RLTrainer._checkpoint": { "total": 0.08601551999981893, "count": 1, "self": 0.08601551999981893 } } } } } } }