{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4777142107486725, "min": 0.43756237626075745, "max": 1.5902884006500244, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14308.49609375, "min": 13112.869140625, "max": 48242.98828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989894.0, "min": 29925.0, "max": 989894.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989894.0, "min": 29925.0, "max": 989894.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.015151633881032467, "min": -0.09408952295780182, "max": 0.27493995428085327, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 3.7121503353118896, "min": -22.769664764404297, "max": 65.1607666015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02167777344584465, "min": 0.012780423276126385, "max": 0.4510452449321747, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.311054706573486, "min": 3.0289602279663086, "max": 109.15294647216797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.03531383852209223, "min": 0.031063595587814536, "max": 0.04054398371767231, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.10594151556627669, "min": 0.09319078676344361, "max": 0.15932182816807958, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.006047606308129616, "min": 0.0008803721258724788, "max": 0.009413041003328907, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.018142818924388848, "min": 0.0030442110555311814, "max": 0.02823912300998672, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5833974722333265e-06, "min": 7.5833974722333265e-06, "max": 0.0002941302019565999, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.275019241669998e-05, "min": 2.275019241669998e-05, "max": 0.0010726746424417999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252776666666667, "min": 0.10252776666666667, "max": 0.19804339999999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.3075833, "min": 0.3075833, "max": 0.7575582000000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00013613555666666655, "min": 0.00013613555666666655, "max": 0.0049023656600000005, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00040840666999999965, "min": 0.00040840666999999965, "max": 0.017882154180000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.021888481453061104, "min": 0.021888481453061104, "max": 0.8063771724700928, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06566544622182846, "min": 0.06566544622182846, "max": 2.4191315174102783, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 791.1111111111111, "min": 791.1111111111111, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28480.0, "min": 15957.0, "max": 32712.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.04191106495757898, "min": -0.9999750521965325, "max": 0.09174701001714258, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 1.5087983384728432, "min": -31.99920167028904, "max": 3.1193983405828476, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.04191106495757898, "min": -0.9999750521965325, "max": 0.09174701001714258, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 1.5087983384728432, "min": -31.99920167028904, "max": 3.1193983405828476, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.17758784054603893, "min": 0.17758784054603893, "max": 13.169016491621733, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.393162259657402, "min": 6.393162259657402, "max": 239.65150392055511, "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": "1768905307", "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": "1768908449" }, "total": 3142.081056051, "count": 1, "self": 0.5841038759995172, "children": { "run_training.setup": { "total": 0.058920113000112906, "count": 1, "self": 0.058920113000112906 }, "TrainerController.start_learning": { "total": 3141.4380320620003, "count": 1, "self": 2.58295364492551, "children": { "TrainerController._reset_env": { "total": 3.759598251999705, "count": 1, "self": 3.759598251999705 }, "TrainerController.advance": { "total": 3135.025784268075, "count": 63243, "self": 2.7039765840668224, "children": { "env_step": { "total": 2237.1938376459684, "count": 63243, "self": 2057.3115365279923, "children": { "SubprocessEnvManager._take_step": { "total": 178.26988093994123, "count": 63243, "self": 7.5526500289961405, "children": { "TorchPolicy.evaluate": { "total": 170.7172309109451, "count": 62580, "self": 170.7172309109451 } } }, "workers": { "total": 1.6124201780348812, "count": 63243, "self": 0.0, "children": { "worker_root": { "total": 3133.06389361394, "count": 63243, "is_parallel": true, "self": 1268.404417387862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00475230099982582, "count": 1, "is_parallel": true, "self": 0.0016317720001097769, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031205289997160435, "count": 8, "is_parallel": true, "self": 0.0031205289997160435 } } }, "UnityEnvironment.step": { "total": 0.07869636400027957, "count": 1, "is_parallel": true, "self": 0.0006771770003979327, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005675140000676038, "count": 1, "is_parallel": true, "self": 0.0005675140000676038 }, "communicator.exchange": { "total": 0.07445971199967971, "count": 1, "is_parallel": true, "self": 0.07445971199967971 }, "steps_from_proto": { "total": 0.0029919610001343244, "count": 1, "is_parallel": true, "self": 0.0005647010011671227, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024272599989672017, "count": 8, "is_parallel": true, "self": 0.0024272599989672017 } } } } } } }, "UnityEnvironment.step": { "total": 1864.659476226078, "count": 63242, "is_parallel": true, "self": 46.734430080159655, "children": { "UnityEnvironment._generate_step_input": { "total": 32.238916343945675, "count": 63242, "is_parallel": true, "self": 32.238916343945675 }, "communicator.exchange": { "total": 1639.4446291290305, "count": 63242, "is_parallel": true, "self": 1639.4446291290305 }, "steps_from_proto": { "total": 146.24150067294204, "count": 63242, "is_parallel": true, "self": 30.330576059859595, "children": { "_process_rank_one_or_two_observation": { "total": 115.91092461308244, "count": 505936, "is_parallel": true, "self": 115.91092461308244 } } } } } } } } } } }, "trainer_advance": { "total": 895.1279700380396, "count": 63243, "self": 4.847024772991517, "children": { "process_trajectory": { "total": 171.88590044104603, "count": 63243, "self": 171.61383980204528, "children": { "RLTrainer._checkpoint": { "total": 0.27206063900075605, "count": 2, "self": 0.27206063900075605 } } }, "_update_policy": { "total": 718.3950448240021, "count": 119, "self": 330.21039703300585, "children": { "TorchPPOOptimizer.update": { "total": 388.1846477909962, "count": 5799, "self": 388.1846477909962 } } } } } } }, "trainer_threads": { "total": 1.059999704011716e-06, "count": 1, "self": 1.059999704011716e-06 }, "TrainerController._save_models": { "total": 0.0696948370004975, "count": 1, "self": 0.0015388510009870515, "children": { "RLTrainer._checkpoint": { "total": 0.06815598599951045, "count": 1, "self": 0.06815598599951045 } } } } } } }