{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30228570103645325, "min": 0.2922554016113281, "max": 1.4273685216903687, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9121.7734375, "min": 8795.71875, "max": 43300.65234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4993949830532074, "min": -0.10080023854970932, "max": 0.5302249193191528, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 137.3336181640625, "min": -24.292858123779297, "max": 145.84133911132812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009546229615807533, "min": 0.009546229615807533, "max": 0.5653338432312012, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.625213146209717, "min": 2.625213146209717, "max": 136.24545288085938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0704258401867254, "min": 0.06564920250370744, "max": 0.07353193825803742, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9859617626141556, "min": 0.5011892835604597, "max": 1.0805387482202302, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015240127936035592, "min": 0.0007548253644344879, "max": 0.031921972516491745, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2133617911044983, "min": 0.009812729737648343, "max": 0.23032031048690746, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.445776089535715e-06, "min": 7.445776089535715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010424086525350001, "min": 0.00010424086525350001, "max": 0.0035081915306028996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248189285714289, "min": 0.10248189285714289, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347465000000004, "min": 1.3886848, "max": 2.5693971, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002579410964285715, "min": 0.0002579410964285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003611175350000001, "min": 0.003611175350000001, "max": 0.11696277028999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0202634334564209, "min": 0.020239263772964478, "max": 0.8803380727767944, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2836880683898926, "min": 0.2833496928215027, "max": 6.1623663902282715, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 415.82191780821915, "min": 354.5421686746988, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30355.0, "min": 15984.0, "max": 32694.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4745671083665874, "min": -1.0000000521540642, "max": 1.6029640869834485, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 107.64339891076088, "min": -29.996201559901237, "max": 131.8033990561962, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4745671083665874, "min": -1.0000000521540642, "max": 1.6029640869834485, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 107.64339891076088, "min": -29.996201559901237, "max": 131.8033990561962, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08695330872512996, "min": 0.07410621169550591, "max": 18.8011967074126, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.3475915369344875, "min": 6.150815570726991, "max": 300.8191473186016, "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": "1757289923", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1757292048" }, "total": 2124.3790936570003, "count": 1, "self": 0.47582563400055733, "children": { "run_training.setup": { "total": 0.02222806899999341, "count": 1, "self": 0.02222806899999341 }, "TrainerController.start_learning": { "total": 2123.881039954, "count": 1, "self": 1.2974695059738224, "children": { "TrainerController._reset_env": { "total": 2.0182314719997976, "count": 1, "self": 2.0182314719997976 }, "TrainerController.advance": { "total": 2120.482685789026, "count": 63852, "self": 1.300398795998717, "children": { "env_step": { "total": 1481.3905273329713, "count": 63852, "self": 1339.373160293856, "children": { "SubprocessEnvManager._take_step": { "total": 141.26178062111308, "count": 63852, "self": 4.428549548046703, "children": { "TorchPolicy.evaluate": { "total": 136.83323107306637, "count": 62544, "self": 136.83323107306637 } } }, "workers": { "total": 0.7555864180021672, "count": 63852, "self": 0.0, "children": { "worker_root": { "total": 2119.1676637719515, "count": 63852, "is_parallel": true, "self": 886.8468092649969, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017102399999657791, "count": 1, "is_parallel": true, "self": 0.000574200000073688, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011360399998920911, "count": 8, "is_parallel": true, "self": 0.0011360399998920911 } } }, "UnityEnvironment.step": { "total": 0.04721835400005148, "count": 1, "is_parallel": true, "self": 0.0005249560001630016, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047397799994541856, "count": 1, "is_parallel": true, "self": 0.00047397799994541856 }, "communicator.exchange": { "total": 0.04462082600002759, "count": 1, "is_parallel": true, "self": 0.04462082600002759 }, "steps_from_proto": { "total": 0.0015985939999154652, "count": 1, "is_parallel": true, "self": 0.00034625199987203814, "children": { "_process_rank_one_or_two_observation": { "total": 0.001252342000043427, "count": 8, "is_parallel": true, "self": 0.001252342000043427 } } } } } } }, "UnityEnvironment.step": { "total": 1232.3208545069547, "count": 63851, "is_parallel": true, "self": 30.826882515025545, "children": { "UnityEnvironment._generate_step_input": { "total": 22.14953346591915, "count": 63851, "is_parallel": true, "self": 22.14953346591915 }, "communicator.exchange": { "total": 1085.6197129609957, "count": 63851, "is_parallel": true, "self": 1085.6197129609957 }, "steps_from_proto": { "total": 93.7247255650143, "count": 63851, "is_parallel": true, "self": 18.540250841859688, "children": { "_process_rank_one_or_two_observation": { "total": 75.18447472315461, "count": 510808, "is_parallel": true, "self": 75.18447472315461 } } } } } } } } } } }, "trainer_advance": { "total": 637.791759660056, "count": 63852, "self": 2.496235900069223, "children": { "process_trajectory": { "total": 123.7634680299891, "count": 63852, "self": 123.5742518619893, "children": { "RLTrainer._checkpoint": { "total": 0.18921616799980256, "count": 2, "self": 0.18921616799980256 } } }, "_update_policy": { "total": 511.53205572999764, "count": 456, "self": 285.78371227295634, "children": { "TorchPPOOptimizer.update": { "total": 225.7483434570413, "count": 22818, "self": 225.7483434570413 } } } } } } }, "trainer_threads": { "total": 1.0069998097606003e-06, "count": 1, "self": 1.0069998097606003e-06 }, "TrainerController._save_models": { "total": 0.08265217999996821, "count": 1, "self": 0.0013219829997979105, "children": { "RLTrainer._checkpoint": { "total": 0.0813301970001703, "count": 1, "self": 0.0813301970001703 } } } } } } }