{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6798476576805115, "min": 0.6478074789047241, "max": 1.475361943244934, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20428.0625, "min": 19195.83203125, "max": 44756.578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3099021911621094, "min": -0.11246249824762344, "max": 0.3712678849697113, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 80.26466369628906, "min": -27.10346221923828, "max": 98.01472473144531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 2.3727941879769787e-05, "min": -0.05568518489599228, "max": 0.4360305964946747, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.00614553689956665, "min": -14.422462463378906, "max": 103.33924865722656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06678804872041968, "min": 0.0656055032921445, "max": 0.07484274155495678, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9350326820858755, "min": 0.49791307864682594, "max": 1.093604081630474, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01239165272896311, "min": 0.0005043793685817227, "max": 0.014534038590465483, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17348313820548353, "min": 0.006556931791562394, "max": 0.20347654026651676, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.502711784842855e-06, "min": 7.502711784842855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010503796498779997, "min": 0.00010503796498779997, "max": 0.0033822797725735, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250087142857144, "min": 0.10250087142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350122, "min": 1.3886848, "max": 2.5274265, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002598370557142857, "min": 0.0002598370557142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036377187799999993, "min": 0.0036377187799999993, "max": 0.11276990734999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007017254829406738, "min": 0.007017254829406738, "max": 0.5353310704231262, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09824156761169434, "min": 0.09824156761169434, "max": 3.747317314147949, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 501.0, "min": 465.7142857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29058.0, "min": 15984.0, "max": 32442.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.257544810273524, "min": -1.0000000521540642, "max": 1.366922779302848, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.93759899586439, "min": -31.998401686549187, "max": 82.65499849617481, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.257544810273524, "min": -1.0000000521540642, "max": 1.366922779302848, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.93759899586439, "min": -31.998401686549187, "max": 82.65499849617481, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0370428636576027, "min": 0.0370428636576027, "max": 10.301259657368064, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1484860921409563, "min": 2.1127294159668963, "max": 164.82015451788902, "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": "1784460817", "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=PyramidsTraining1 --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": "1784463163" }, "total": 2346.10893074, "count": 1, "self": 0.4788377209997634, "children": { "run_training.setup": { "total": 0.024693117999959213, "count": 1, "self": 0.024693117999959213 }, "TrainerController.start_learning": { "total": 2345.605399901, "count": 1, "self": 1.3344938490554341, "children": { "TrainerController._reset_env": { "total": 2.237502867000103, "count": 1, "self": 2.237502867000103 }, "TrainerController.advance": { "total": 2341.9590013519446, "count": 63535, "self": 1.3590550590365638, "children": { "env_step": { "total": 1703.738152525952, "count": 63535, "self": 1551.268401795965, "children": { "SubprocessEnvManager._take_step": { "total": 151.6873631150113, "count": 63535, "self": 4.685535588994753, "children": { "TorchPolicy.evaluate": { "total": 147.00182752601654, "count": 62560, "self": 147.00182752601654 } } }, "workers": { "total": 0.7823876149757325, "count": 63535, "self": 0.0, "children": { "worker_root": { "total": 2339.8430449009325, "count": 63535, "is_parallel": true, "self": 908.2355875099024, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017774840000583936, "count": 1, "is_parallel": true, "self": 0.0005491320000601263, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012283519999982673, "count": 8, "is_parallel": true, "self": 0.0012283519999982673 } } }, "UnityEnvironment.step": { "total": 0.0533096869999099, "count": 1, "is_parallel": true, "self": 0.0006348819999857369, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005400899999585818, "count": 1, "is_parallel": true, "self": 0.0005400899999585818 }, "communicator.exchange": { "total": 0.05018956399999297, "count": 1, "is_parallel": true, "self": 0.05018956399999297 }, "steps_from_proto": { "total": 0.0019451509999726113, "count": 1, "is_parallel": true, "self": 0.0003891489998295583, "children": { "_process_rank_one_or_two_observation": { "total": 0.001556002000143053, "count": 8, "is_parallel": true, "self": 0.001556002000143053 } } } } } } }, "UnityEnvironment.step": { "total": 1431.60745739103, "count": 63534, "is_parallel": true, "self": 34.54778862687385, "children": { "UnityEnvironment._generate_step_input": { "total": 24.207666043037534, "count": 63534, "is_parallel": true, "self": 24.207666043037534 }, "communicator.exchange": { "total": 1260.7016004980824, "count": 63534, "is_parallel": true, "self": 1260.7016004980824 }, "steps_from_proto": { "total": 112.15040222303628, "count": 63534, "is_parallel": true, "self": 23.226561036163048, "children": { "_process_rank_one_or_two_observation": { "total": 88.92384118687323, "count": 508272, "is_parallel": true, "self": 88.92384118687323 } } } } } } } } } } }, "trainer_advance": { "total": 636.861793766956, "count": 63535, "self": 2.592488263925361, "children": { "process_trajectory": { "total": 110.58991535403015, "count": 63535, "self": 110.32814584602988, "children": { "RLTrainer._checkpoint": { "total": 0.26176950800027043, "count": 2, "self": 0.26176950800027043 } } }, "_update_policy": { "total": 523.6793901490005, "count": 450, "self": 279.9255365599861, "children": { "TorchPPOOptimizer.update": { "total": 243.7538535890144, "count": 22800, "self": 243.7538535890144 } } } } } } }, "trainer_threads": { "total": 1.2450000212993473e-06, "count": 1, "self": 1.2450000212993473e-06 }, "TrainerController._save_models": { "total": 0.0744005879996621, "count": 1, "self": 0.0010467559995959164, "children": { "RLTrainer._checkpoint": { "total": 0.07335383200006618, "count": 1, "self": 0.07335383200006618 } } } } } } }