{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3323372006416321, "min": 0.32964062690734863, "max": 1.478977918624878, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9986.068359375, "min": 9889.21875, "max": 44866.2734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46786218881607056, "min": -0.12279345840215683, "max": 0.49270832538604736, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.7906494140625, "min": -29.593223571777344, "max": 133.52395629882812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04735676571726799, "min": -0.04735676571726799, "max": 0.2960365414619446, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -12.833683013916016, "min": -12.833683013916016, "max": 70.16065979003906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06560912435359603, "min": 0.06428209158289094, "max": 0.07406775116213174, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9185277409503445, "min": 0.49284443807829675, "max": 1.0798831626501244, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013681606453842924, "min": 0.00016508147400152022, "max": 0.014764888375967056, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19154249035380094, "min": 0.0021460591620197627, "max": 0.21395556042376018, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.69156172189286e-06, "min": 7.69156172189286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010768186410650005, "min": 0.00010768186410650005, "max": 0.003507942230686, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256382142857141, "min": 0.10256382142857141, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358934999999997, "min": 1.3886848, "max": 2.569314, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002661257607142858, "min": 0.0002661257607142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037257606500000016, "min": 0.0037257606500000016, "max": 0.1169544686, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00974547304213047, "min": 0.00974547304213047, "max": 0.49629831314086914, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13643662631511688, "min": 0.13643662631511688, "max": 3.474088191986084, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 395.93506493506493, "min": 382.6, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30487.0, "min": 15984.0, "max": 33922.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4962026122957468, "min": -1.0000000521540642, "max": 1.4962026122957468, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.71139853447676, "min": -31.99480167031288, "max": 117.3653985708952, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4962026122957468, "min": -1.0000000521540642, "max": 1.4962026122957468, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.71139853447676, "min": -31.99480167031288, "max": 117.3653985708952, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040564607169423984, "min": 0.039371671824301305, "max": 11.015428492799401, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.082910144876223, "min": 3.082910144876223, "max": 176.24685588479042, "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": "1686349020", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1686351085" }, "total": 2065.2660667439995, "count": 1, "self": 0.4745711959994878, "children": { "run_training.setup": { "total": 0.03966016300000774, "count": 1, "self": 0.03966016300000774 }, "TrainerController.start_learning": { "total": 2064.751835385, "count": 1, "self": 1.3241851569505343, "children": { "TrainerController._reset_env": { "total": 4.637470330000042, "count": 1, "self": 4.637470330000042 }, "TrainerController.advance": { "total": 2058.69995867705, "count": 63752, "self": 1.308405204176779, "children": { "env_step": { "total": 1431.1051913729398, "count": 63752, "self": 1324.3077036029267, "children": { "SubprocessEnvManager._take_step": { "total": 106.04073506597501, "count": 63752, "self": 4.698721686998397, "children": { "TorchPolicy.evaluate": { "total": 101.34201337897662, "count": 62562, "self": 101.34201337897662 } } }, "workers": { "total": 0.7567527040380355, "count": 63752, "self": 0.0, "children": { "worker_root": { "total": 2060.266632368995, "count": 63752, "is_parallel": true, "self": 845.0242341509759, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021478030000707804, "count": 1, "is_parallel": true, "self": 0.0006850629999917146, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014627400000790658, "count": 8, "is_parallel": true, "self": 0.0014627400000790658 } } }, "UnityEnvironment.step": { "total": 0.07786578499985808, "count": 1, "is_parallel": true, "self": 0.0005715029999464605, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004581929999858403, "count": 1, "is_parallel": true, "self": 0.0004581929999858403 }, "communicator.exchange": { "total": 0.0748986920000334, "count": 1, "is_parallel": true, "self": 0.0748986920000334 }, "steps_from_proto": { "total": 0.0019373969998923712, "count": 1, "is_parallel": true, "self": 0.00037252200013426773, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015648749997581035, "count": 8, "is_parallel": true, "self": 0.0015648749997581035 } } } } } } }, "UnityEnvironment.step": { "total": 1215.2423982180192, "count": 63751, "is_parallel": true, "self": 32.052620559048364, "children": { "UnityEnvironment._generate_step_input": { "total": 21.93304728197245, "count": 63751, "is_parallel": true, "self": 21.93304728197245 }, "communicator.exchange": { "total": 1063.9831814990057, "count": 63751, "is_parallel": true, "self": 1063.9831814990057 }, "steps_from_proto": { "total": 97.27354887799265, "count": 63751, "is_parallel": true, "self": 18.839962757149806, "children": { "_process_rank_one_or_two_observation": { "total": 78.43358612084285, "count": 510008, "is_parallel": true, "self": 78.43358612084285 } } } } } } } } } } }, "trainer_advance": { "total": 626.2863620999331, "count": 63752, "self": 2.495642249940829, "children": { "process_trajectory": { "total": 106.71427668799015, "count": 63752, "self": 106.51529158499034, "children": { "RLTrainer._checkpoint": { "total": 0.19898510299981353, "count": 2, "self": 0.19898510299981353 } } }, "_update_policy": { "total": 517.0764431620021, "count": 452, "self": 332.547666369039, "children": { "TorchPPOOptimizer.update": { "total": 184.52877679296307, "count": 22782, "self": 184.52877679296307 } } } } } } }, "trainer_threads": { "total": 8.319998414663132e-07, "count": 1, "self": 8.319998414663132e-07 }, "TrainerController._save_models": { "total": 0.09022038900002372, "count": 1, "self": 0.0013406110001596971, "children": { "RLTrainer._checkpoint": { "total": 0.08887977799986402, "count": 1, "self": 0.08887977799986402 } } } } } } }