{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6934102773666382, "min": 0.6745714545249939, "max": 1.4631102085113525, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20702.45703125, "min": 20150.798828125, "max": 44384.91015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20361100137233734, "min": -0.13542723655700684, "max": 0.20361100137233734, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 51.920806884765625, "min": -32.096256256103516, "max": 51.920806884765625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.19911488890647888, "min": 0.01804698072373867, "max": 0.4217011630535126, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 50.774295806884766, "min": 4.349322319030762, "max": 101.20828247070312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06449348936981622, "min": 0.06413171239945964, "max": 0.07421490162188453, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.902908851177427, "min": 0.48523599023535313, "max": 1.0298669329974526, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014976870682436508, "min": 7.232142720461897e-05, "max": 0.014976870682436508, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2096761895541111, "min": 0.0010124999808646656, "max": 0.2096761895541111, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.597340324728573e-06, "min": 7.597340324728573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010636276454620003, "min": 0.00010636276454620003, "max": 0.0032557049147651, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253241428571429, "min": 0.10253241428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354538000000001, "min": 1.3691136000000002, "max": 2.3852349, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002629881871428573, "min": 0.0002629881871428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003681834620000002, "min": 0.003681834620000002, "max": 0.10854496651000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016609277576208115, "min": 0.016609277576208115, "max": 0.5913077592849731, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2325298935174942, "min": 0.2325298935174942, "max": 4.139154434204102, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 672.4318181818181, "min": 672.4318181818181, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29587.0, "min": 15984.0, "max": 33436.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7364863250404596, "min": -1.0000000521540642, "max": 0.7364863250404596, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 32.405398301780224, "min": -32.000001668930054, "max": 32.405398301780224, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7364863250404596, "min": -1.0000000521540642, "max": 0.7364863250404596, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 32.405398301780224, "min": -32.000001668930054, "max": 32.405398301780224, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11711653845056637, "min": 0.11711653845056637, "max": 12.477840095758438, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.1531276918249205, "min": 5.033200995065272, "max": 199.645441532135, "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": "1712904076", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712906031" }, "total": 1955.1136022010003, "count": 1, "self": 0.4895655190002799, "children": { "run_training.setup": { "total": 0.04855234800015751, "count": 1, "self": 0.04855234800015751 }, "TrainerController.start_learning": { "total": 1954.5754843339998, "count": 1, "self": 1.23401496098586, "children": { "TrainerController._reset_env": { "total": 2.230292125999995, "count": 1, "self": 2.230292125999995 }, "TrainerController.advance": { "total": 1951.0244794650139, "count": 63227, "self": 1.353996692026385, "children": { "env_step": { "total": 1334.5167301789695, "count": 63227, "self": 1210.0324815859096, "children": { "SubprocessEnvManager._take_step": { "total": 123.71662630607102, "count": 63227, "self": 4.426764573089031, "children": { "TorchPolicy.evaluate": { "total": 119.28986173298199, "count": 62569, "self": 119.28986173298199 } } }, "workers": { "total": 0.7676222869888534, "count": 63227, "self": 0.0, "children": { "worker_root": { "total": 1949.8848670379343, "count": 63227, "is_parallel": true, "self": 851.026072879976, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020467740000640333, "count": 1, "is_parallel": true, "self": 0.000612486999898465, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014342870001655683, "count": 8, "is_parallel": true, "self": 0.0014342870001655683 } } }, "UnityEnvironment.step": { "total": 0.10841299100002288, "count": 1, "is_parallel": true, "self": 0.0006472490001669939, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004771129999880941, "count": 1, "is_parallel": true, "self": 0.0004771129999880941 }, "communicator.exchange": { "total": 0.10543688400002793, "count": 1, "is_parallel": true, "self": 0.10543688400002793 }, "steps_from_proto": { "total": 0.001851744999839866, "count": 1, "is_parallel": true, "self": 0.00039367900035358616, "children": { "_process_rank_one_or_two_observation": { "total": 0.00145806599948628, "count": 8, "is_parallel": true, "self": 0.00145806599948628 } } } } } } }, "UnityEnvironment.step": { "total": 1098.8587941579583, "count": 63226, "is_parallel": true, "self": 33.45813928491816, "children": { "UnityEnvironment._generate_step_input": { "total": 23.097775213997238, "count": 63226, "is_parallel": true, "self": 23.097775213997238 }, "communicator.exchange": { "total": 946.7239358080117, "count": 63226, "is_parallel": true, "self": 946.7239358080117 }, "steps_from_proto": { "total": 95.57894385103123, "count": 63226, "is_parallel": true, "self": 18.807738437941907, "children": { "_process_rank_one_or_two_observation": { "total": 76.77120541308932, "count": 505808, "is_parallel": true, "self": 76.77120541308932 } } } } } } } } } } }, "trainer_advance": { "total": 615.153752594018, "count": 63227, "self": 2.2930042369828243, "children": { "process_trajectory": { "total": 123.12713578103353, "count": 63227, "self": 122.92651839003315, "children": { "RLTrainer._checkpoint": { "total": 0.20061739100037812, "count": 2, "self": 0.20061739100037812 } } }, "_update_policy": { "total": 489.73361257600163, "count": 437, "self": 288.32583582399434, "children": { "TorchPPOOptimizer.update": { "total": 201.4077767520073, "count": 22830, "self": 201.4077767520073 } } } } } } }, "trainer_threads": { "total": 1.0379999366705306e-06, "count": 1, "self": 1.0379999366705306e-06 }, "TrainerController._save_models": { "total": 0.08669674400016447, "count": 1, "self": 0.0013907240004300547, "children": { "RLTrainer._checkpoint": { "total": 0.08530601999973442, "count": 1, "self": 0.08530601999973442 } } } } } } }