{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5105743408203125, "min": 0.5105743408203125, "max": 1.4153269529342651, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15366.24609375, "min": 15366.24609375, "max": 42935.359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38944900035858154, "min": -0.1186157688498497, "max": 0.4265997111797333, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.03563690185547, "min": -28.586400985717773, "max": 114.75532531738281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0021599363535642624, "min": -0.013654683716595173, "max": 0.3989749252796173, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5659033060073853, "min": -3.6184911727905273, "max": 95.75398254394531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07017989390892797, "min": 0.06558731864095621, "max": 0.07477418569673414, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9825185147249916, "min": 0.523419299877139, "max": 1.0575968790685246, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015139511283147536, "min": 0.00029311721278402707, "max": 0.015512501832518592, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2119531579640655, "min": 0.003224289340624298, "max": 0.21717502565526028, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.38629039507857e-06, "min": 7.38629039507857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010340806553109998, "min": 0.00010340806553109998, "max": 0.003382871972376099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246206428571429, "min": 0.10246206428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344689000000002, "min": 1.3886848, "max": 2.5276239, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025596022214285707, "min": 0.00025596022214285707, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003583443109999999, "min": 0.003583443109999999, "max": 0.11278962761, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01492005679756403, "min": 0.01492005679756403, "max": 0.49722275137901306, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20888079702854156, "min": 0.20888079702854156, "max": 3.4805593490600586, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 452.3636363636364, "min": 413.2837837837838, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29856.0, "min": 15984.0, "max": 33582.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3354636131588258, "min": -1.0000000521540642, "max": 1.5056026822610482, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 88.1405984684825, "min": -30.997601613402367, "max": 111.41459848731756, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3354636131588258, "min": -1.0000000521540642, "max": 1.5056026822610482, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 88.1405984684825, "min": -30.997601613402367, "max": 111.41459848731756, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07002738876833588, "min": 0.0680472015944385, "max": 10.237286988645792, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.621807658710168, "min": 4.584234749956522, "max": 163.79659181833267, "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": "1702881324", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702883365" }, "total": 2041.207688415, "count": 1, "self": 0.6875162319997798, "children": { "run_training.setup": { "total": 0.05083875499985879, "count": 1, "self": 0.05083875499985879 }, "TrainerController.start_learning": { "total": 2040.4693334280003, "count": 1, "self": 1.2664978919792702, "children": { "TrainerController._reset_env": { "total": 2.08179599600021, "count": 1, "self": 2.08179599600021 }, "TrainerController.advance": { "total": 2036.9992384270208, "count": 63477, "self": 1.3579070339569626, "children": { "env_step": { "total": 1398.5533217770694, "count": 63477, "self": 1272.947818342996, "children": { "SubprocessEnvManager._take_step": { "total": 124.82659982002565, "count": 63477, "self": 4.599146297052357, "children": { "TorchPolicy.evaluate": { "total": 120.22745352297329, "count": 62565, "self": 120.22745352297329 } } }, "workers": { "total": 0.7789036140477492, "count": 63477, "self": 0.0, "children": { "worker_root": { "total": 2035.672002071055, "count": 63477, "is_parallel": true, "self": 876.9947957390425, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016633759998967435, "count": 1, "is_parallel": true, "self": 0.0005098349997751939, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011535410001215496, "count": 8, "is_parallel": true, "self": 0.0011535410001215496 } } }, "UnityEnvironment.step": { "total": 0.052268015999970885, "count": 1, "is_parallel": true, "self": 0.0006409050001821015, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004923209999105893, "count": 1, "is_parallel": true, "self": 0.0004923209999105893 }, "communicator.exchange": { "total": 0.04936148100000537, "count": 1, "is_parallel": true, "self": 0.04936148100000537 }, "steps_from_proto": { "total": 0.0017733089998728246, "count": 1, "is_parallel": true, "self": 0.0003570699998363125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014162390000365122, "count": 8, "is_parallel": true, "self": 0.0014162390000365122 } } } } } } }, "UnityEnvironment.step": { "total": 1158.6772063320125, "count": 63476, "is_parallel": true, "self": 34.51350880409109, "children": { "UnityEnvironment._generate_step_input": { "total": 24.371749653911365, "count": 63476, "is_parallel": true, "self": 24.371749653911365 }, "communicator.exchange": { "total": 1002.9668501379958, "count": 63476, "is_parallel": true, "self": 1002.9668501379958 }, "steps_from_proto": { "total": 96.82509773601419, "count": 63476, "is_parallel": true, "self": 18.899482530899604, "children": { "_process_rank_one_or_two_observation": { "total": 77.92561520511458, "count": 507808, "is_parallel": true, "self": 77.92561520511458 } } } } } } } } } } }, "trainer_advance": { "total": 637.0880096159945, "count": 63477, "self": 2.4892717900133903, "children": { "process_trajectory": { "total": 125.79276093197791, "count": 63477, "self": 125.56745761197794, "children": { "RLTrainer._checkpoint": { "total": 0.22530331999996633, "count": 2, "self": 0.22530331999996633 } } }, "_update_policy": { "total": 508.80597689400315, "count": 444, "self": 302.1853591020515, "children": { "TorchPPOOptimizer.update": { "total": 206.62061779195164, "count": 22851, "self": 206.62061779195164 } } } } } } }, "trainer_threads": { "total": 1.5300001905416138e-06, "count": 1, "self": 1.5300001905416138e-06 }, "TrainerController._save_models": { "total": 0.12179958299975624, "count": 1, "self": 0.0020343119995231973, "children": { "RLTrainer._checkpoint": { "total": 0.11976527100023304, "count": 1, "self": 0.11976527100023304 } } } } } } }