{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2442646473646164, "min": 0.2261277437210083, "max": 1.5105721950531006, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 7327.939453125, "min": 6758.505859375, "max": 45824.71875, "count": 50 }, "Pyramids.Step.mean": { "value": 1499937.0, "min": 29952.0, "max": 1499937.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499937.0, "min": 29952.0, "max": 1499937.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6769136190414429, "min": -0.1423654556274414, "max": 0.80181485414505, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 197.65878295898438, "min": -33.7406120300293, "max": 235.7335662841797, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01067463867366314, "min": -0.016158170998096466, "max": 0.30701127648353577, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.1169943809509277, "min": -4.265757083892822, "max": 72.76167297363281, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06842641357313066, "min": 0.06551125563975588, "max": 0.07445021473917736, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9579697900238292, "min": 0.48385824580059983, "max": 1.0721061553728455, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01551709126943024, "min": 0.00018117131781538733, "max": 0.015980392635572657, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21723927777202337, "min": 0.0019928844959692608, "max": 0.2372229104609384, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.891970464614291e-06, "min": 2.891970464614291e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.0487586504600075e-05, "min": 4.0487586504600075e-05, "max": 0.003654758781747132, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10096395714285715, "min": 0.10096395714285715, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4134954000000002, "min": 1.3794090666666667, "max": 2.6182528666666665, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010629931857142876, "min": 0.00010629931857142876, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0014881904600000026, "min": 0.0014881904600000026, "max": 0.12184346137999999, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010403135791420937, "min": 0.010388905182480812, "max": 0.3661195933818817, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1456439048051834, "min": 0.1456439048051834, "max": 2.5628371238708496, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 262.38260869565215, "min": 226.3153846153846, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30174.0, "min": 15984.0, "max": 32648.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7376173759284226, "min": -1.0000000521540642, "max": 1.77368459884937, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 199.8259982317686, "min": -32.000001668930054, "max": 230.5789978504181, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7376173759284226, "min": -1.0000000521540642, "max": 1.77368459884937, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 199.8259982317686, "min": -32.000001668930054, "max": 230.5789978504181, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028192082255997737, "min": 0.025587592207739363, "max": 7.273940280079842, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2420894594397396, "min": 3.223189543117769, "max": 116.38304448127747, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1750987510", "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 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750990938" }, "total": 3427.697477525, "count": 1, "self": 0.4821277270002611, "children": { "run_training.setup": { "total": 0.022112502000027234, "count": 1, "self": 0.022112502000027234 }, "TrainerController.start_learning": { "total": 3427.193237296, "count": 1, "self": 1.8935727590351235, "children": { "TrainerController._reset_env": { "total": 3.1529189709999628, "count": 1, "self": 3.1529189709999628 }, "TrainerController.advance": { "total": 3422.0567551709646, "count": 96481, "self": 1.949643928932801, "children": { "env_step": { "total": 2425.367287508053, "count": 96481, "self": 2212.074327416214, "children": { "SubprocessEnvManager._take_step": { "total": 212.1862386489413, "count": 96481, "self": 6.640379043020175, "children": { "TorchPolicy.evaluate": { "total": 205.54585960592112, "count": 93808, "self": 205.54585960592112 } } }, "workers": { "total": 1.1067214428971965, "count": 96481, "self": 0.0, "children": { "worker_root": { "total": 3420.2012240480326, "count": 96481, "is_parallel": true, "self": 1367.045297622959, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0048300829998879635, "count": 1, "is_parallel": true, "self": 0.0033311409995349095, "children": { "_process_rank_one_or_two_observation": { "total": 0.001498942000353054, "count": 8, "is_parallel": true, "self": 0.001498942000353054 } } }, "UnityEnvironment.step": { "total": 0.04773567400002321, "count": 1, "is_parallel": true, "self": 0.0006043129997124197, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004599080000389222, "count": 1, "is_parallel": true, "self": 0.0004599080000389222 }, "communicator.exchange": { "total": 0.04504021900015687, "count": 1, "is_parallel": true, "self": 0.04504021900015687 }, "steps_from_proto": { "total": 0.0016312340001150005, "count": 1, "is_parallel": true, "self": 0.0003321750007216906, "children": { "_process_rank_one_or_two_observation": { "total": 0.00129905899939331, "count": 8, "is_parallel": true, "self": 0.00129905899939331 } } } } } } }, "UnityEnvironment.step": { "total": 2053.1559264250736, "count": 96480, "is_parallel": true, "self": 47.2978455379282, "children": { "UnityEnvironment._generate_step_input": { "total": 33.18454536507261, "count": 96480, "is_parallel": true, "self": 33.18454536507261 }, "communicator.exchange": { "total": 1831.9307249610692, "count": 96480, "is_parallel": true, "self": 1831.9307249610692 }, "steps_from_proto": { "total": 140.74281056100358, "count": 96480, "is_parallel": true, "self": 27.627038561961626, "children": { "_process_rank_one_or_two_observation": { "total": 113.11577199904195, "count": 771840, "is_parallel": true, "self": 113.11577199904195 } } } } } } } } } } }, "trainer_advance": { "total": 994.7398237339789, "count": 96481, "self": 3.7403897969988975, "children": { "process_trajectory": { "total": 188.77273703797823, "count": 96481, "self": 188.41634868697815, "children": { "RLTrainer._checkpoint": { "total": 0.3563883510000778, "count": 3, "self": 0.3563883510000778 } } }, "_update_policy": { "total": 802.2266968990018, "count": 681, "self": 443.49087584494873, "children": { "TorchPPOOptimizer.update": { "total": 358.7358210540531, "count": 34218, "self": 358.7358210540531 } } } } } } }, "trainer_threads": { "total": 1.3250000847619958e-06, "count": 1, "self": 1.3250000847619958e-06 }, "TrainerController._save_models": { "total": 0.08998907000022882, "count": 1, "self": 0.0012366410001050099, "children": { "RLTrainer._checkpoint": { "total": 0.08875242900012381, "count": 1, "self": 0.08875242900012381 } } } } } } }