{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.319823294878006, "min": 0.31257733702659607, "max": 0.5975245237350464, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 9584.46484375, "min": 6609.93408203125, "max": 17677.166015625, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 293.5809523809524, "min": 257.52, "max": 481.61290322580646, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30826.0, "min": 6438.0, "max": 31763.0, "count": 17 }, "Pyramids.Step.mean": { "value": 1289947.0, "min": 809986.0, "max": 1289947.0, "count": 17 }, "Pyramids.Step.sum": { "value": 1289947.0, "min": 809986.0, "max": 1289947.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.619970977306366, "min": 0.3787713050842285, "max": 0.6907874941825867, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.6917266845703, "min": 46.155460357666016, "max": 196.8744354248047, "count": 17 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07412516325712204, "min": -0.021012531593441963, "max": 0.22361399233341217, "count": 17 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.12567138671875, "min": -5.967558860778809, "max": 55.17997741699219, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.649259035715035, "min": 1.2070225576960272, "max": 1.7424799865484237, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.17219875007868, "min": 43.561999663710594, "max": 181.79999859631062, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.649259035715035, "min": 1.2070225576960272, "max": 1.7424799865484237, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.17219875007868, "min": 43.561999663710594, "max": 181.79999859631062, "count": 17 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02859027630689698, "min": 0.02859027630689698, "max": 0.051359173181774694, "count": 17 }, "Pyramids.Policy.RndReward.sum": { "value": 3.001979012224183, "min": 0.7479011392279062, "max": 3.487852165621007, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06484048874376135, "min": 0.06432744616629658, "max": 0.07214679845969267, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9726073311564202, "min": 0.26503267175091116, "max": 1.0559722722246079, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018301821046043183, "min": 0.00944948837648207, "max": 0.018301821046043183, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.27452731569064776, "min": 0.06729381944751367, "max": 0.27452731569064776, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.702344253097432e-06, "min": 5.702344253097432e-06, "max": 0.00011415196579551923, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 8.553516379646147e-05, "min": 8.553516379646147e-05, "max": 0.0015401550635383843, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10190074871794871, "min": 0.10190074871794871, "max": 0.13805063461538464, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5285112307692308, "min": 0.5522025384615386, "max": 2.013384692307693, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.00019988479692307682, "min": 0.00019988479692307682, "max": 0.0038112583980769235, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.002998271953846152, "min": 0.002998271953846152, "max": 0.05143713076153847, "count": 17 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009405708871781826, "min": 0.009405708871781826, "max": 0.011365039274096489, "count": 17 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1410856395959854, "min": 0.045460157096385956, "max": 0.16461586952209473, "count": 17 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1778922534", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [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": "1778924461" }, "total": 1926.8520317700004, "count": 1, "self": 0.6344367049996436, "children": { "run_training.setup": { "total": 0.03414629500002775, "count": 1, "self": 0.03414629500002775 }, "TrainerController.start_learning": { "total": 1926.1834487700007, "count": 1, "self": 1.1642636581045736, "children": { "TrainerController._reset_env": { "total": 2.6059098300002006, "count": 1, "self": 2.6059098300002006 }, "TrainerController.advance": { "total": 1922.331510840896, "count": 32494, "self": 1.2426296366538736, "children": { "env_step": { "total": 1390.2430358881384, "count": 32494, "self": 1309.2883962230671, "children": { "SubprocessEnvManager._take_step": { "total": 80.22493141208543, "count": 32494, "self": 3.7135870762813283, "children": { "TorchPolicy.evaluate": { "total": 76.5113443358041, "count": 31314, "self": 76.5113443358041 } } }, "workers": { "total": 0.7297082529858017, "count": 32494, "self": 0.0, "children": { "worker_root": { "total": 1922.0152365621243, "count": 32494, "is_parallel": true, "self": 705.909340012181, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022964939998928457, "count": 1, "is_parallel": true, "self": 0.0007643669978278922, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015321270020649536, "count": 8, "is_parallel": true, "self": 0.0015321270020649536 } } }, "UnityEnvironment.step": { "total": 0.14022891300010087, "count": 1, "is_parallel": true, "self": 0.0006791680007154355, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005537010001717135, "count": 1, "is_parallel": true, "self": 0.0005537010001717135 }, "communicator.exchange": { "total": 0.13484162599979754, "count": 1, "is_parallel": true, "self": 0.13484162599979754 }, "steps_from_proto": { "total": 0.004154417999416182, "count": 1, "is_parallel": true, "self": 0.0004496060000747093, "children": { "_process_rank_one_or_two_observation": { "total": 0.003704811999341473, "count": 8, "is_parallel": true, "self": 0.003704811999341473 } } } } } } }, "UnityEnvironment.step": { "total": 1216.1058965499433, "count": 32493, "is_parallel": true, "self": 23.459624602023723, "children": { "UnityEnvironment._generate_step_input": { "total": 16.086272527030815, "count": 32493, "is_parallel": true, "self": 16.086272527030815 }, "communicator.exchange": { "total": 1103.9503507469317, "count": 32493, "is_parallel": true, "self": 1103.9503507469317 }, "steps_from_proto": { "total": 72.60964867395705, "count": 32493, "is_parallel": true, "self": 14.79374144988833, "children": { "_process_rank_one_or_two_observation": { "total": 57.815907224068724, "count": 259944, "is_parallel": true, "self": 57.815907224068724 } } } } } } } } } } }, "trainer_advance": { "total": 530.8458453161038, "count": 32494, "self": 2.497868041001311, "children": { "process_trajectory": { "total": 80.2237972310968, "count": 32494, "self": 80.04370109409592, "children": { "RLTrainer._checkpoint": { "total": 0.18009613700087357, "count": 1, "self": 0.18009613700087357 } } }, "_update_policy": { "total": 448.1241800440057, "count": 236, "self": 178.62058678103767, "children": { "TorchPPOOptimizer.update": { "total": 269.503593262968, "count": 11364, "self": 269.503593262968 } } } } } } }, "trainer_threads": { "total": 1.1140000424347818e-06, "count": 1, "self": 1.1140000424347818e-06 }, "TrainerController._save_models": { "total": 0.08176332699986233, "count": 1, "self": 0.002271391000249423, "children": { "RLTrainer._checkpoint": { "total": 0.0794919359996129, "count": 1, "self": 0.0794919359996129 } } } } } } }