{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41320616006851196, "min": 0.41320616006851196, "max": 1.4852380752563477, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12449.0751953125, "min": 12449.0751953125, "max": 38972.6484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6240072846412659, "min": -0.09642890095710754, "max": 0.6393569707870483, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 175.34605407714844, "min": -23.239364624023438, "max": 183.49545288085938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009985915385186672, "min": 0.002595818368718028, "max": 0.3473924994468689, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.806042194366455, "min": 0.7164458632469177, "max": 83.72159576416016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750413520977094, "min": 0.06431173062422982, "max": 0.0726640624149392, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9450578929367932, "min": 0.4316297037456381, "max": 1.0782752536858122, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01741611656781934, "min": 0.0007273732061702858, "max": 0.01741611656781934, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24382563194947077, "min": 0.010183224886384002, "max": 0.2587577999414255, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5526831967571434e-06, "min": 7.5526831967571434e-06, "max": 0.0002946048017984, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010573756475460001, "min": 0.00010573756475460001, "max": 0.0033825260724914, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251752857142858, "min": 0.10251752857142858, "max": 0.19820159999999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352454000000001, "min": 1.1892095999999999, "max": 2.5275086, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026150110428571437, "min": 0.00026150110428571437, "max": 0.00982033984, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036610154600000013, "min": 0.0036610154600000013, "max": 0.11277810914, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0182869303971529, "min": 0.0182869303971529, "max": 0.6112358570098877, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2560170292854309, "min": 0.2560170292854309, "max": 3.667415142059326, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.96190476190475, "min": 294.56190476190477, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31181.0, "min": 15984.0, "max": 33065.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6272552261749904, "min": -1.0000000521540642, "max": 1.6855422943257368, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 170.86179874837399, "min": -30.992001608014107, "max": 175.29639860987663, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6272552261749904, "min": -1.0000000521540642, "max": 1.6855422943257368, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 170.86179874837399, "min": -30.992001608014107, "max": 175.29639860987663, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.055965538503646495, "min": 0.055965538503646495, "max": 11.01230601966381, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.876381542882882, "min": 5.630166640941752, "max": 176.19689631462097, "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": "1701533384", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701537875" }, "total": 4490.946439645, "count": 1, "self": 2.176551821999965, "children": { "run_training.setup": { "total": 0.17438058100015041, "count": 1, "self": 0.17438058100015041 }, "TrainerController.start_learning": { "total": 4488.595507242, "count": 1, "self": 3.6984144371408547, "children": { "TrainerController._reset_env": { "total": 10.776521396000135, "count": 1, "self": 10.776521396000135 }, "TrainerController.advance": { "total": 4473.95222662686, "count": 63761, "self": 5.142288076880504, "children": { "env_step": { "total": 2522.281007677932, "count": 63761, "self": 2192.5812538330088, "children": { "SubprocessEnvManager._take_step": { "total": 328.39859001596005, "count": 63761, "self": 12.135641457001384, "children": { "TorchPolicy.evaluate": { "total": 316.26294855895867, "count": 62305, "self": 316.26294855895867 } } }, "workers": { "total": 1.3011638289631264, "count": 63761, "self": 0.0, "children": { "worker_root": { "total": 4484.185641512061, "count": 63761, "is_parallel": true, "self": 2604.7252189940205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026039099998342863, "count": 1, "is_parallel": true, "self": 0.0007515289994444174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018523810003898689, "count": 8, "is_parallel": true, "self": 0.0018523810003898689 } } }, "UnityEnvironment.step": { "total": 0.10212740900033168, "count": 1, "is_parallel": true, "self": 0.0006307549997472961, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004512510004133219, "count": 1, "is_parallel": true, "self": 0.0004512510004133219 }, "communicator.exchange": { "total": 0.09938192900017384, "count": 1, "is_parallel": true, "self": 0.09938192900017384 }, "steps_from_proto": { "total": 0.0016634739999972226, "count": 1, "is_parallel": true, "self": 0.00034190099950137665, "children": { "_process_rank_one_or_two_observation": { "total": 0.001321573000495846, "count": 8, "is_parallel": true, "self": 0.001321573000495846 } } } } } } }, "UnityEnvironment.step": { "total": 1879.4604225180406, "count": 63760, "is_parallel": true, "self": 34.91603148725153, "children": { "UnityEnvironment._generate_step_input": { "total": 22.265774597900418, "count": 63760, "is_parallel": true, "self": 22.265774597900418 }, "communicator.exchange": { "total": 1725.3798560939194, "count": 63760, "is_parallel": true, "self": 1725.3798560939194 }, "steps_from_proto": { "total": 96.89876033896917, "count": 63760, "is_parallel": true, "self": 18.437097057763822, "children": { "_process_rank_one_or_two_observation": { "total": 78.46166328120535, "count": 510080, "is_parallel": true, "self": 78.46166328120535 } } } } } } } } } } }, "trainer_advance": { "total": 1946.5289308720476, "count": 63761, "self": 9.212012804005099, "children": { "process_trajectory": { "total": 411.18268439704434, "count": 63761, "self": 410.68693661604493, "children": { "RLTrainer._checkpoint": { "total": 0.49574778099940886, "count": 2, "self": 0.49574778099940886 } } }, "_update_policy": { "total": 1526.1342336709981, "count": 451, "self": 1041.735780137053, "children": { "TorchPPOOptimizer.update": { "total": 484.39845353394503, "count": 22674, "self": 484.39845353394503 } } } } } } }, "trainer_threads": { "total": 1.2049995348206721e-06, "count": 1, "self": 1.2049995348206721e-06 }, "TrainerController._save_models": { "total": 0.16834357700008695, "count": 1, "self": 0.003110988999651454, "children": { "RLTrainer._checkpoint": { "total": 0.1652325880004355, "count": 1, "self": 0.1652325880004355 } } } } } } }