| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.2793838083744049, | |
| "min": 0.2724528908729553, | |
| "max": 1.4045430421829224, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 8394.9248046875, | |
| "min": 8129.994140625, | |
| "max": 42608.21875, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989963.0, | |
| "min": 29936.0, | |
| "max": 989963.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989963.0, | |
| "min": 29936.0, | |
| "max": 989963.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.5149140954017639, | |
| "min": -0.16957752406597137, | |
| "max": 0.5974474549293518, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 139.54171752929688, | |
| "min": -40.35945129394531, | |
| "max": 167.3739776611328, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.011843646876513958, | |
| "min": -0.0007899208576418459, | |
| "max": 0.24504907429218292, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 3.2096283435821533, | |
| "min": -0.2014298141002655, | |
| "max": 58.321678161621094, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.0710304126554143, | |
| "min": 0.06620332666177757, | |
| "max": 0.07211202205077939, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9944257771758, | |
| "min": 0.6481071698124649, | |
| "max": 1.0792192596699084, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.014543584698075724, | |
| "min": 0.0008878538220956489, | |
| "max": 0.015174544091652411, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.20361018577306014, | |
| "min": 0.012429953509339085, | |
| "max": 0.21244361728313377, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.391540393328573e-06, | |
| "min": 7.391540393328573e-06, | |
| "max": 0.0002947996350667889, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00010348156550660002, | |
| "min": 0.00010348156550660002, | |
| "max": 0.0037609783463406006, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.1024638142857143, | |
| "min": 0.1024638142857143, | |
| "max": 0.19826654444444444, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4344934000000003, | |
| "min": 1.4344934000000003, | |
| "max": 2.6536594, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 1.221743285714286e-05, | |
| "min": 1.221743285714286e-05, | |
| "max": 9.843989e-05, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.00017104406000000003, | |
| "min": 0.00017104406000000003, | |
| "max": 0.0012682934600000003, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.009209325537085533, | |
| "min": 0.009209325537085533, | |
| "max": 0.3078683614730835, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.12893055379390717, | |
| "min": 0.12893055379390717, | |
| "max": 2.770815372467041, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 350.3658536585366, | |
| "min": 321.67391304347825, | |
| "max": 987.8965517241379, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 28730.0, | |
| "min": 17374.0, | |
| "max": 33435.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.550711088894326, | |
| "min": -0.9223867153127988, | |
| "max": 1.6783260703086853, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 125.6075982004404, | |
| "min": -27.671601459383965, | |
| "max": 154.40599846839905, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.550711088894326, | |
| "min": -0.9223867153127988, | |
| "max": 1.6783260703086853, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 125.6075982004404, | |
| "min": -27.671601459383965, | |
| "max": 154.40599846839905, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.03440499107747189, | |
| "min": 0.03291260615997484, | |
| "max": 6.479283852709664, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.7868042772752233, | |
| "min": 2.7868042772752233, | |
| "max": 116.62710934877396, | |
| "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": "1736310810", | |
| "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", | |
| "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": "2.5.1+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1736313494" | |
| }, | |
| "total": 2684.202191773001, | |
| "count": 1, | |
| "self": 0.4859085520010922, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.08197609899980307, | |
| "count": 1, | |
| "self": 0.08197609899980307 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2683.634307122, | |
| "count": 1, | |
| "self": 1.3117702789058967, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.7289770879997377, | |
| "count": 1, | |
| "self": 2.7289770879997377 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2679.5061498310934, | |
| "count": 63906, | |
| "self": 1.4176261610718939, | |
| "children": { | |
| "env_step": { | |
| "total": 1617.425940036007, | |
| "count": 63906, | |
| "self": 1470.1424979020458, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 146.51791245806635, | |
| "count": 63906, | |
| "self": 4.598733186003301, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 141.91917927206305, | |
| "count": 62551, | |
| "self": 141.91917927206305 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.765529675894868, | |
| "count": 63906, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2678.647450231978, | |
| "count": 63906, | |
| "is_parallel": true, | |
| "self": 1325.1281930567184, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0031829740000830498, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0009291080004913965, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0022538659995916532, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0022538659995916532 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04660641299960844, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005795859997306252, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00048162799976125825, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00048162799976125825 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04391936299998633, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04391936299998633 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0016258360001302208, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00037562499983323505, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012502110002969857, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012502110002969857 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1353.5192571752596, | |
| "count": 63905, | |
| "is_parallel": true, | |
| "self": 32.9346385255858, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 23.532905073042457, | |
| "count": 63905, | |
| "is_parallel": true, | |
| "self": 23.532905073042457 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1198.4234069427484, | |
| "count": 63905, | |
| "is_parallel": true, | |
| "self": 1198.4234069427484 | |
| }, | |
| "steps_from_proto": { | |
| "total": 98.62830663388286, | |
| "count": 63905, | |
| "is_parallel": true, | |
| "self": 19.94277071423585, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 78.68553591964701, | |
| "count": 511240, | |
| "is_parallel": true, | |
| "self": 78.68553591964701 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1060.6625836340145, | |
| "count": 63906, | |
| "self": 2.559596860844067, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 133.62849662718054, | |
| "count": 63906, | |
| "self": 133.22707814717887, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.40141848000166647, | |
| "count": 2, | |
| "self": 0.40141848000166647 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 924.4744901459899, | |
| "count": 464, | |
| "self": 521.2807173690344, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 403.1937727769555, | |
| "count": 37950, | |
| "self": 403.1937727769555 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.0309995559509844e-06, | |
| "count": 1, | |
| "self": 1.0309995559509844e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.08740889300133858, | |
| "count": 1, | |
| "self": 0.0014752560000488302, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.08593363700128975, | |
| "count": 1, | |
| "self": 0.08593363700128975 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |