{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16100628674030304, "min": 0.1550900638103485, "max": 1.5024821758270264, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4825.03662109375, "min": 4640.7099609375, "max": 45579.30078125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999977.0, "min": 29952.0, "max": 2999977.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999977.0, "min": 29952.0, "max": 2999977.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.795719563961029, "min": -0.2318664789199829, "max": 0.894476592540741, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 239.5115966796875, "min": -54.952354431152344, "max": 277.2877502441406, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008244006894528866, "min": -0.03826584666967392, "max": 0.3161642849445343, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.4814460277557373, "min": -11.135361671447754, "max": 74.93093872070312, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06582640466582407, "min": 0.06383411356459161, "max": 0.07383711195133895, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.921569665321537, "min": 0.46283001699832793, "max": 1.1075566792700842, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016050468924471973, "min": 0.00038251659405899217, "max": 0.016516931564813434, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22470656494260763, "min": 0.004207682534648914, "max": 0.2477539734722015, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.434035236307143e-06, "min": 1.434035236307143e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.00764933083e-05, "min": 2.00764933083e-05, "max": 0.0038923584025472666, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047797857142858, "min": 0.10047797857142858, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066917, "min": 1.3962282666666668, "max": 2.797452733333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.775005928571428e-05, "min": 5.775005928571428e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008085008299999999, "min": 0.0008085008299999999, "max": 0.12976552806, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005431185010820627, "min": 0.005371715873479843, "max": 0.27355095744132996, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07603658735752106, "min": 0.0752040222287178, "max": 1.9148567914962769, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 209.79850746268656, "min": 205.3581081081081, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28113.0, "min": 15984.0, "max": 32919.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7902014808201079, "min": -1.0000000521540642, "max": 1.7902014808201079, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 239.88699842989445, "min": -30.46480169892311, "max": 263.605998583138, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7902014808201079, "min": -1.0000000521540642, "max": 1.7902014808201079, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 239.88699842989445, "min": -30.46480169892311, "max": 263.605998583138, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011726893565822532, "min": 0.011726893565822532, "max": 5.358835105784237, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5714037378202192, "min": 1.5714037378202192, "max": 85.7413616925478, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691040574", "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": "1691048316" }, "total": 7741.618685645, "count": 1, "self": 0.4805571279994183, "children": { "run_training.setup": { "total": 0.047914781000031326, "count": 1, "self": 0.047914781000031326 }, "TrainerController.start_learning": { "total": 7741.090213736001, "count": 1, "self": 4.756210301042302, "children": { "TrainerController._reset_env": { "total": 5.550462664999998, "count": 1, "self": 5.550462664999998 }, "TrainerController.advance": { "total": 7730.616227234959, "count": 195055, "self": 4.853124087121614, "children": { "env_step": { "total": 5668.831644262876, "count": 195055, "self": 5305.251893111987, "children": { "SubprocessEnvManager._take_step": { "total": 360.6397259568746, "count": 195055, "self": 15.714182646784991, "children": { "TorchPolicy.evaluate": { "total": 344.9255433100896, "count": 187556, "self": 344.9255433100896 } } }, "workers": { "total": 2.9400251940140265, "count": 195055, "self": 0.0, "children": { "worker_root": { "total": 7722.5269272049045, "count": 195055, "is_parallel": true, "self": 2807.3814763907776, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00543364399999291, "count": 1, "is_parallel": true, "self": 0.0039187189999552174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015149250000376924, "count": 8, "is_parallel": true, "self": 0.0015149250000376924 } } }, "UnityEnvironment.step": { "total": 0.04999730300005467, "count": 1, "is_parallel": true, "self": 0.0006185240000036174, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005047340000032818, "count": 1, "is_parallel": true, "self": 0.0005047340000032818 }, "communicator.exchange": { "total": 0.047051484000007804, "count": 1, "is_parallel": true, "self": 0.047051484000007804 }, "steps_from_proto": { "total": 0.0018225610000399683, "count": 1, "is_parallel": true, "self": 0.00034915000003366004, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014734110000063083, "count": 8, "is_parallel": true, "self": 0.0014734110000063083 } } } } } } }, "UnityEnvironment.step": { "total": 4915.145450814127, "count": 195054, "is_parallel": true, "self": 111.00655539781746, "children": { "UnityEnvironment._generate_step_input": { "total": 76.96378800833463, "count": 195054, "is_parallel": true, "self": 76.96378800833463 }, "communicator.exchange": { "total": 4376.998074799991, "count": 195054, "is_parallel": true, "self": 4376.998074799991 }, "steps_from_proto": { "total": 350.1770326079844, "count": 195054, "is_parallel": true, "self": 71.72513992930755, "children": { "_process_rank_one_or_two_observation": { "total": 278.45189267867687, "count": 1560432, "is_parallel": true, "self": 278.45189267867687 } } } } } } } } } } }, "trainer_advance": { "total": 2056.931458884962, "count": 195055, "self": 9.324995909247718, "children": { "process_trajectory": { "total": 371.1405191617318, "count": 195055, "self": 370.2753441537313, "children": { "RLTrainer._checkpoint": { "total": 0.8651750080005058, "count": 6, "self": 0.8651750080005058 } } }, "_update_policy": { "total": 1676.4659438139824, "count": 1388, "self": 1094.2300227660307, "children": { "TorchPPOOptimizer.update": { "total": 582.2359210479517, "count": 68379, "self": 582.2359210479517 } } } } } } }, "trainer_threads": { "total": 1.2599994079209864e-06, "count": 1, "self": 1.2599994079209864e-06 }, "TrainerController._save_models": { "total": 0.16731227499985835, "count": 1, "self": 0.0019612490004874417, "children": { "RLTrainer._checkpoint": { "total": 0.1653510259993709, "count": 1, "self": 0.1653510259993709 } } } } } } }