{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4002004861831665, "min": 0.3868868052959442, "max": 1.4120850563049316, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12146.884765625, "min": 11612.7939453125, "max": 42837.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5814646482467651, "min": -0.11426528543233871, "max": 0.5814646482467651, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.32131958007812, "min": -27.652198791503906, "max": 159.32131958007812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007775426842272282, "min": -0.0005932306521572173, "max": 0.3761492967605591, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.130466938018799, "min": -0.15957903861999512, "max": 90.21241760253906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07261004518759413, "min": 0.06452094166048078, "max": 0.07490646960163237, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0165406326263178, "min": 0.5068145774252346, "max": 1.0937924106935195, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016343720488419027, "min": 0.0009334105824416415, "max": 0.016343720488419027, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22881208683786639, "min": 0.013067748154182981, "max": 0.22881208683786639, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.306318993164284e-06, "min": 7.306318993164284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010228846590429998, "min": 0.00010228846590429998, "max": 0.0035043602318799998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243540714285716, "min": 0.10243540714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340957000000003, "min": 1.3886848, "max": 2.56812, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002532971735714286, "min": 0.0002532971735714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035461604300000005, "min": 0.0035461604300000005, "max": 0.116835188, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013144395314157009, "min": 0.013144395314157009, "max": 0.5550200343132019, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18402153253555298, "min": 0.18402153253555298, "max": 3.8851404190063477, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 338.48837209302326, "min": 332.39325842696627, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29110.0, "min": 15984.0, "max": 33624.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5917209085336952, "min": -1.0000000521540642, "max": 1.6033088695671824, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 136.88799813389778, "min": -30.413801662623882, "max": 144.2977982610464, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5917209085336952, "min": -1.0000000521540642, "max": 1.6033088695671824, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 136.88799813389778, "min": -30.413801662623882, "max": 144.2977982610464, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04597545426601522, "min": 0.04597545426601522, "max": 11.507040472701192, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9538890668773092, "min": 3.858002293665777, "max": 184.11264756321907, "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": "1742669616", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742672122" }, "total": 2505.9440800840002, "count": 1, "self": 0.5366475690007064, "children": { "run_training.setup": { "total": 0.022009776999766473, "count": 1, "self": 0.022009776999766473 }, "TrainerController.start_learning": { "total": 2505.3854227379998, "count": 1, "self": 1.6762286549519558, "children": { "TrainerController._reset_env": { "total": 2.2521976739999445, "count": 1, "self": 2.2521976739999445 }, "TrainerController.advance": { "total": 2501.3602479410483, "count": 63927, "self": 1.7182194690435608, "children": { "env_step": { "total": 1767.6586060349282, "count": 63927, "self": 1586.5046328429394, "children": { "SubprocessEnvManager._take_step": { "total": 180.19878203199005, "count": 63927, "self": 5.3274690899538655, "children": { "TorchPolicy.evaluate": { "total": 174.87131294203618, "count": 62571, "self": 174.87131294203618 } } }, "workers": { "total": 0.9551911599987761, "count": 63927, "self": 0.0, "children": { "worker_root": { "total": 2499.4785925520982, "count": 63927, "is_parallel": true, "self": 1043.7775967379766, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022528270001203055, "count": 1, "is_parallel": true, "self": 0.0007556109999313776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014972160001889279, "count": 8, "is_parallel": true, "self": 0.0014972160001889279 } } }, "UnityEnvironment.step": { "total": 0.051015310999900976, "count": 1, "is_parallel": true, "self": 0.0006281460005084227, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005183789999136934, "count": 1, "is_parallel": true, "self": 0.0005183789999136934 }, "communicator.exchange": { "total": 0.048068132999560476, "count": 1, "is_parallel": true, "self": 0.048068132999560476 }, "steps_from_proto": { "total": 0.001800652999918384, "count": 1, "is_parallel": true, "self": 0.0004012279996459256, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013994250002724584, "count": 8, "is_parallel": true, "self": 0.0013994250002724584 } } } } } } }, "UnityEnvironment.step": { "total": 1455.7009958141216, "count": 63926, "is_parallel": true, "self": 35.19505370516981, "children": { "UnityEnvironment._generate_step_input": { "total": 26.088609135999832, "count": 63926, "is_parallel": true, "self": 26.088609135999832 }, "communicator.exchange": { "total": 1285.0654224749383, "count": 63926, "is_parallel": true, "self": 1285.0654224749383 }, "steps_from_proto": { "total": 109.3519104980137, "count": 63926, "is_parallel": true, "self": 22.823676796022482, "children": { "_process_rank_one_or_two_observation": { "total": 86.52823370199121, "count": 511408, "is_parallel": true, "self": 86.52823370199121 } } } } } } } } } } }, "trainer_advance": { "total": 731.9834224370766, "count": 63927, "self": 3.2155660941421047, "children": { "process_trajectory": { "total": 139.8991397509426, "count": 63927, "self": 139.67924459794222, "children": { "RLTrainer._checkpoint": { "total": 0.21989515300037965, "count": 2, "self": 0.21989515300037965 } } }, "_update_policy": { "total": 588.8687165919919, "count": 454, "self": 325.96765919497284, "children": { "TorchPPOOptimizer.update": { "total": 262.90105739701903, "count": 22809, "self": 262.90105739701903 } } } } } } }, "trainer_threads": { "total": 9.539999155094847e-07, "count": 1, "self": 9.539999155094847e-07 }, "TrainerController._save_models": { "total": 0.09674751399961679, "count": 1, "self": 0.0015475560003324063, "children": { "RLTrainer._checkpoint": { "total": 0.09519995799928438, "count": 1, "self": 0.09519995799928438 } } } } } } }