{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35985761880874634, "min": 0.35985761880874634, "max": 1.4951326847076416, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10795.728515625, "min": 10795.728515625, "max": 45356.34375, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5342896580696106, "min": -0.1031314879655838, "max": 0.5835443735122681, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.99822998046875, "min": -24.751556396484375, "max": 162.225341796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07662080228328705, "min": 0.005290832370519638, "max": 0.3707778751850128, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.223962783813477, "min": 1.4655605554580688, "max": 87.87435913085938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0699764938546448, "min": 0.06461131780942138, "max": 0.07445865809194828, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.049647407819672, "min": 0.4876640665618537, "max": 1.064885815702534, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016659237832775235, "min": 0.0005577779979327816, "max": 0.0171608928571162, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24988856749162852, "min": 0.005020001981395034, "max": 0.24988856749162852, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.529517490193337e-06, "min": 7.529517490193337e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011294276235290006, "min": 0.00011294276235290006, "max": 0.0031402454532515997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250980666666668, "min": 0.10250980666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376471, "min": 1.3886848, "max": 2.3591434000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002607296860000002, "min": 0.0002607296860000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003910945290000003, "min": 0.003910945290000003, "max": 0.10470016516000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008241442032158375, "min": 0.008241442032158375, "max": 0.41470035910606384, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1236216276884079, "min": 0.12111823260784149, "max": 2.902902603149414, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.01162790697674, "min": 312.6559139784946, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30101.0, "min": 15984.0, "max": 32746.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6034534608208857, "min": -1.0000000521540642, "max": 1.6869467910616955, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.89699763059616, "min": -32.000001668930054, "max": 158.57299835979939, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6034534608208857, "min": -1.0000000521540642, "max": 1.6869467910616955, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.89699763059616, "min": -32.000001668930054, "max": 158.57299835979939, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03027926326924285, "min": 0.02932243299994994, "max": 9.626343991607428, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6040166411548853, "min": 2.6040166411548853, "max": 154.02150386571884, "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": "1696299834", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1696301328" }, "total": 1494.221681776, "count": 1, "self": 0.3715608290003729, "children": { "run_training.setup": { "total": 0.0368238249998285, "count": 1, "self": 0.0368238249998285 }, "TrainerController.start_learning": { "total": 1493.8132971219998, "count": 1, "self": 1.1219425989074807, "children": { "TrainerController._reset_env": { "total": 3.9152243789999375, "count": 1, "self": 3.9152243789999375 }, "TrainerController.advance": { "total": 1488.6744268830926, "count": 63734, "self": 1.1059112360617291, "children": { "env_step": { "total": 959.1052888610316, "count": 63734, "self": 866.1538795100514, "children": { "SubprocessEnvManager._take_step": { "total": 92.24969461195587, "count": 63734, "self": 4.084840258845816, "children": { "TorchPolicy.evaluate": { "total": 88.16485435311006, "count": 62571, "self": 88.16485435311006 } } }, "workers": { "total": 0.7017147390242826, "count": 63734, "self": 0.0, "children": { "worker_root": { "total": 1491.5637796100864, "count": 63734, "is_parallel": true, "self": 708.9701621941354, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020317079997766996, "count": 1, "is_parallel": true, "self": 0.0006464570001298853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013852509996468143, "count": 8, "is_parallel": true, "self": 0.0013852509996468143 } } }, "UnityEnvironment.step": { "total": 0.03692010199983997, "count": 1, "is_parallel": true, "self": 0.0005853449993082904, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046128300027703517, "count": 1, "is_parallel": true, "self": 0.00046128300027703517 }, "communicator.exchange": { "total": 0.03320803199994771, "count": 1, "is_parallel": true, "self": 0.03320803199994771 }, "steps_from_proto": { "total": 0.002665442000306939, "count": 1, "is_parallel": true, "self": 0.00039341100045930943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022720309998476296, "count": 8, "is_parallel": true, "self": 0.0022720309998476296 } } } } } } }, "UnityEnvironment.step": { "total": 782.593617415951, "count": 63733, "is_parallel": true, "self": 19.833430586002123, "children": { "UnityEnvironment._generate_step_input": { "total": 13.715115770032753, "count": 63733, "is_parallel": true, "self": 13.715115770032753 }, "communicator.exchange": { "total": 687.0952267099374, "count": 63733, "is_parallel": true, "self": 687.0952267099374 }, "steps_from_proto": { "total": 61.949844349978775, "count": 63733, "is_parallel": true, "self": 12.661483756780854, "children": { "_process_rank_one_or_two_observation": { "total": 49.28836059319792, "count": 509864, "is_parallel": true, "self": 49.28836059319792 } } } } } } } } } } }, "trainer_advance": { "total": 528.4632267859993, "count": 63734, "self": 2.1194749950759615, "children": { "process_trajectory": { "total": 91.85608259792525, "count": 63734, "self": 91.61878305192522, "children": { "RLTrainer._checkpoint": { "total": 0.23729954600003111, "count": 2, "self": 0.23729954600003111 } } }, "_update_policy": { "total": 434.48766919299806, "count": 439, "self": 274.83267077303617, "children": { "TorchPPOOptimizer.update": { "total": 159.65499841996188, "count": 22803, "self": 159.65499841996188 } } } } } } }, "trainer_threads": { "total": 1.219999830937013e-06, "count": 1, "self": 1.219999830937013e-06 }, "TrainerController._save_models": { "total": 0.10170204099995317, "count": 1, "self": 0.0014082210000196937, "children": { "RLTrainer._checkpoint": { "total": 0.10029381999993348, "count": 1, "self": 0.10029381999993348 } } } } } } }