{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37783801555633545, "min": 0.3408486545085907, "max": 1.3605443239212036, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11407.685546875, "min": 10209.0986328125, "max": 32914.2890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29951.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29951.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2156532108783722, "min": -0.17285645008087158, "max": 0.28188860416412354, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 54.56026077270508, "min": -32.66986846923828, "max": 73.00914764404297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03783803433179855, "min": 0.0030573680996894836, "max": 0.472737580537796, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.573022842407227, "min": 0.7735141515731812, "max": 89.45181274414062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06721809591648967, "min": 0.06562428259092164, "max": 0.07318220606786134, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9410533428308553, "min": 0.40870321522695424, "max": 1.062153641302846, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008414831094601791, "min": 0.000695455142374161, "max": 0.015856676001355433, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11780763532442506, "min": 0.009040916850864092, "max": 0.1697651332591811, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.317204703821425e-06, "min": 7.317204703821425e-06, "max": 0.0002942925519024833, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010244086585349996, "min": 0.00010244086585349996, "max": 0.0034910743363085993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243903571428573, "min": 0.10243903571428573, "max": 0.19809751666666667, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341465000000002, "min": 1.1885851, "max": 2.4852986, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025365966785714274, "min": 0.00025365966785714274, "max": 0.009809941915, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035512353499999984, "min": 0.0035512353499999984, "max": 0.11638277086, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.027771679684519768, "min": 0.027766002342104912, "max": 0.5217909216880798, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.38880351185798645, "min": 0.38872402906417847, "max": 3.1307456493377686, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 629.4468085106383, "min": 529.6071428571429, "max": 998.9375, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29584.0, "min": 15983.0, "max": 32644.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7320467832874744, "min": -0.9341125530190766, "max": 1.1131106953003578, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 34.4061988145113, "min": -29.89160169661045, "max": 62.33419893682003, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7320467832874744, "min": -0.9341125530190766, "max": 1.1131106953003578, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 34.4061988145113, "min": -29.89160169661045, "max": 62.33419893682003, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.17808634871765575, "min": 0.15359965654418126, "max": 9.569400081411004, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 8.37005838972982, "min": 8.064975622051861, "max": 153.11040130257607, "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": "1781877410", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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 --resume", "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": "1781879735" }, "total": 2325.3920998160006, "count": 1, "self": 0.47915704200113396, "children": { "run_training.setup": { "total": 0.02286060299957171, "count": 1, "self": 0.02286060299957171 }, "TrainerController.start_learning": { "total": 2324.890082171, "count": 1, "self": 1.3180784369728826, "children": { "TrainerController._reset_env": { "total": 2.1514990559999205, "count": 1, "self": 2.1514990559999205 }, "TrainerController.advance": { "total": 2321.3433243000272, "count": 62999, "self": 1.3640972560515365, "children": { "env_step": { "total": 1703.7966754910885, "count": 62999, "self": 1552.2669364380813, "children": { "SubprocessEnvManager._take_step": { "total": 150.7262089540136, "count": 62999, "self": 4.574016635930093, "children": { "TorchPolicy.evaluate": { "total": 146.1521923180835, "count": 62165, "self": 146.1521923180835 } } }, "workers": { "total": 0.8035300989936331, "count": 62999, "self": 0.0, "children": { "worker_root": { "total": 2319.3881338460696, "count": 62999, "is_parallel": true, "self": 882.3121545960785, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018806130001394195, "count": 1, "is_parallel": true, "self": 0.0006665560003966675, "children": { "_process_rank_one_or_two_observation": { "total": 0.001214056999742752, "count": 8, "is_parallel": true, "self": 0.001214056999742752 } } }, "UnityEnvironment.step": { "total": 0.05128879899984895, "count": 1, "is_parallel": true, "self": 0.0005539949997910298, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005001140002605098, "count": 1, "is_parallel": true, "self": 0.0005001140002605098 }, "communicator.exchange": { "total": 0.04863773399983984, "count": 1, "is_parallel": true, "self": 0.04863773399983984 }, "steps_from_proto": { "total": 0.0015969559999575722, "count": 1, "is_parallel": true, "self": 0.00038586499977100175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012110910001865705, "count": 8, "is_parallel": true, "self": 0.0012110910001865705 } } } } } } }, "UnityEnvironment.step": { "total": 1437.0759792499912, "count": 62998, "is_parallel": true, "self": 33.40167111589244, "children": { "UnityEnvironment._generate_step_input": { "total": 23.166133541987165, "count": 62998, "is_parallel": true, "self": 23.166133541987165 }, "communicator.exchange": { "total": 1274.2417032561098, "count": 62998, "is_parallel": true, "self": 1274.2417032561098 }, "steps_from_proto": { "total": 106.26647133600181, "count": 62998, "is_parallel": true, "self": 22.144776773895046, "children": { "_process_rank_one_or_two_observation": { "total": 84.12169456210677, "count": 503984, "is_parallel": true, "self": 84.12169456210677 } } } } } } } } } } }, "trainer_advance": { "total": 616.1825515528872, "count": 62999, "self": 2.5511752717175114, "children": { "process_trajectory": { "total": 109.11603575416211, "count": 62999, "self": 108.92333363416265, "children": { "RLTrainer._checkpoint": { "total": 0.19270211999946696, "count": 2, "self": 0.19270211999946696 } } }, "_update_policy": { "total": 504.51534052700754, "count": 452, "self": 266.3646412810058, "children": { "TorchPPOOptimizer.update": { "total": 238.15069924600175, "count": 22662, "self": 238.15069924600175 } } } } } } }, "trainer_threads": { "total": 1.0900002962443978e-06, "count": 1, "self": 1.0900002962443978e-06 }, "TrainerController._save_models": { "total": 0.07717928799957008, "count": 1, "self": 0.0014161479994072579, "children": { "RLTrainer._checkpoint": { "total": 0.07576314000016282, "count": 1, "self": 0.07576314000016282 } } } } } } }