{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39741361141204834, "min": 0.39249035716056824, "max": 1.4532856941223145, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11909.69140625, "min": 11862.62890625, "max": 44086.875, "count": 33 }, "Pyramids.Step.mean": { "value": 989923.0, "min": 29908.0, "max": 989923.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989923.0, "min": 29908.0, "max": 989923.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5347685813903809, "min": -0.17452983558177948, "max": 0.5899375081062317, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 148.66566467285156, "min": -41.88716125488281, "max": 165.18251037597656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027728794142603874, "min": 0.020704900845885277, "max": 0.28993433713912964, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.70860481262207, "min": 5.631732940673828, "max": 69.58424377441406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06950068172729863, "min": 0.06431823449190337, "max": 0.07379303142669637, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9730095441821809, "min": 0.48822231280056083, "max": 1.0733340622003502, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0159675119000548, "min": 0.0005375435335923741, "max": 0.0159675119000548, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2235451666007672, "min": 0.007525609470293237, "max": 0.23024166489873704, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.348426121985716e-06, "min": 7.348426121985716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010287796570780002, "min": 0.00010287796570780002, "max": 0.0034921117359627994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244944285714286, "min": 0.10244944285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342922, "min": 1.3886848, "max": 2.4862022, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002546993414285715, "min": 0.0002546993414285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003565790780000001, "min": 0.003565790780000001, "max": 0.11641731628, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.024407463148236275, "min": 0.024407463148236275, "max": 0.5852988958358765, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.34170448780059814, "min": 0.34170448780059814, "max": 4.097092151641846, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 348.08045977011494, "min": 348.08045977011494, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30283.0, "min": 16835.0, "max": 33561.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6079636156897654, "min": -0.9999871489501768, "max": 1.6450246657118386, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 141.50079818069935, "min": -30.999601617455482, "max": 141.50079818069935, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6079636156897654, "min": -0.9999871489501768, "max": 1.6450246657118386, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 141.50079818069935, "min": -30.999601617455482, "max": 141.50079818069935, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.086326377301041, "min": 0.086326377301041, "max": 11.227535291629678, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 7.596721202491608, "min": 7.52142452186672, "max": 190.86809995770454, "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": "1747367502", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/home/gym/.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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747368319" }, "total": 816.9601381419999, "count": 1, "self": 0.218148676999931, "children": { "run_training.setup": { "total": 0.013524332999963917, "count": 1, "self": 0.013524332999963917 }, "TrainerController.start_learning": { "total": 816.728465132, "count": 1, "self": 0.5930147309869653, "children": { "TrainerController._reset_env": { "total": 1.228264455000044, "count": 1, "self": 1.228264455000044 }, "TrainerController.advance": { "total": 814.8787214330132, "count": 63705, "self": 0.5560394840263143, "children": { "env_step": { "total": 611.2338976199959, "count": 63705, "self": 573.3734891499769, "children": { "SubprocessEnvManager._take_step": { "total": 37.48590162500534, "count": 63705, "self": 1.6912241119889586, "children": { "TorchPolicy.evaluate": { "total": 35.79467751301638, "count": 62546, "self": 35.79467751301638 } } }, "workers": { "total": 0.37450684501368414, "count": 63705, "self": 0.0, "children": { "worker_root": { "total": 815.2489232009905, "count": 63705, "is_parallel": true, "self": 281.63628776701626, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012136119999013317, "count": 1, "is_parallel": true, "self": 0.0006440639999709674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005695479999303643, "count": 8, "is_parallel": true, "self": 0.0005695479999303643 } } }, "UnityEnvironment.step": { "total": 0.01830171100004918, "count": 1, "is_parallel": true, "self": 0.00014197400003013172, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00012826400006815675, "count": 1, "is_parallel": true, "self": 0.00012826400006815675 }, "communicator.exchange": { "total": 0.017659118999972634, "count": 1, "is_parallel": true, "self": 0.017659118999972634 }, "steps_from_proto": { "total": 0.0003723539999782588, "count": 1, "is_parallel": true, "self": 9.316300008777034e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00027919099989048846, "count": 8, "is_parallel": true, "self": 0.00027919099989048846 } } } } } } }, "UnityEnvironment.step": { "total": 533.6126354339742, "count": 63704, "is_parallel": true, "self": 7.515094199031523, "children": { "UnityEnvironment._generate_step_input": { "total": 5.0651114539650735, "count": 63704, "is_parallel": true, "self": 5.0651114539650735 }, "communicator.exchange": { "total": 500.51337489298567, "count": 63704, "is_parallel": true, "self": 500.51337489298567 }, "steps_from_proto": { "total": 20.519054887991956, "count": 63704, "is_parallel": true, "self": 4.689604202042119, "children": { "_process_rank_one_or_two_observation": { "total": 15.829450685949837, "count": 509632, "is_parallel": true, "self": 15.829450685949837 } } } } } } } } } } }, "trainer_advance": { "total": 203.08878432899098, "count": 63705, "self": 1.1527257959716053, "children": { "process_trajectory": { "total": 40.00459650002142, "count": 63705, "self": 39.93416578702147, "children": { "RLTrainer._checkpoint": { "total": 0.07043071299995063, "count": 2, "self": 0.07043071299995063 } } }, "_update_policy": { "total": 161.93146203299796, "count": 452, "self": 85.87127631300405, "children": { "TorchPPOOptimizer.update": { "total": 76.06018571999391, "count": 22827, "self": 76.06018571999391 } } } } } } }, "trainer_threads": { "total": 4.75999968330143e-07, "count": 1, "self": 4.75999968330143e-07 }, "TrainerController._save_models": { "total": 0.028464036999821474, "count": 1, "self": 0.0006103279999933875, "children": { "RLTrainer._checkpoint": { "total": 0.027853708999828086, "count": 1, "self": 0.027853708999828086 } } } } } } }