{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5581293106079102, "min": 0.5581293106079102, "max": 1.439385175704956, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16859.970703125, "min": 16859.970703125, "max": 43665.1875, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43074777722358704, "min": -0.09208530187606812, "max": 0.4683237671852112, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 115.4404067993164, "min": -22.19255828857422, "max": 125.51077270507812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.09759559482336044, "min": -0.09759559482336044, "max": 0.2728722393512726, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -26.15561866760254, "min": -26.15561866760254, "max": 65.48933410644531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0679318716159157, "min": 0.06577663904185413, "max": 0.07145455162210783, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9510462026228197, "min": 0.4975253171585206, "max": 1.0102592974309994, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.020319339279099256, "min": 0.000731553295118104, "max": 0.020319339279099256, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2844707499073896, "min": 0.008263571422984329, "max": 0.2844707499073896, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.741040276828574e-06, "min": 7.741040276828574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010837456387560002, "min": 0.00010837456387560002, "max": 0.0036333820888727, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258031428571428, "min": 0.10258031428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361244, "min": 1.3691136000000002, "max": 2.6111272999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002677733971428573, "min": 0.0002677733971428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003748827560000002, "min": 0.003748827560000002, "max": 0.12113161727000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01144792977720499, "min": 0.01144792977720499, "max": 0.43646901845932007, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16027101874351501, "min": 0.16027101874351501, "max": 3.0552830696105957, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 406.4931506849315, "min": 406.4931506849315, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29674.0, "min": 15984.0, "max": 33356.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.538695863562904, "min": -1.0000000521540642, "max": 1.538695863562904, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.32479804009199, "min": -32.000001668930054, "max": 112.32479804009199, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.538695863562904, "min": -1.0000000521540642, "max": 1.538695863562904, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.32479804009199, "min": -32.000001668930054, "max": 112.32479804009199, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04838300331843354, "min": 0.04838300331843354, "max": 8.860677578486502, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.531959242245648, "min": 3.531959242245648, "max": 141.77084125578403, "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": "1688005829", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688007914" }, "total": 2084.4290468689996, "count": 1, "self": 0.848004619999756, "children": { "run_training.setup": { "total": 0.06350630799988721, "count": 1, "self": 0.06350630799988721 }, "TrainerController.start_learning": { "total": 2083.517535941, "count": 1, "self": 1.3925342711618214, "children": { "TrainerController._reset_env": { "total": 4.105239557999994, "count": 1, "self": 4.105239557999994 }, "TrainerController.advance": { "total": 2077.874770710838, "count": 63522, "self": 1.4022931269569199, "children": { "env_step": { "total": 1441.0381771679272, "count": 63522, "self": 1329.691235021905, "children": { "SubprocessEnvManager._take_step": { "total": 110.55479534307733, "count": 63522, "self": 4.666730950134934, "children": { "TorchPolicy.evaluate": { "total": 105.8880643929424, "count": 62565, "self": 105.8880643929424 } } }, "workers": { "total": 0.7921468029448988, "count": 63522, "self": 0.0, "children": { "worker_root": { "total": 2078.8484248280115, "count": 63522, "is_parallel": true, "self": 860.8763362070454, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017542230002618453, "count": 1, "is_parallel": true, "self": 0.00054593400000158, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012082890002602653, "count": 8, "is_parallel": true, "self": 0.0012082890002602653 } } }, "UnityEnvironment.step": { "total": 0.04963784499977919, "count": 1, "is_parallel": true, "self": 0.0005630069999824627, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004726819997813436, "count": 1, "is_parallel": true, "self": 0.0004726819997813436 }, "communicator.exchange": { "total": 0.046720806999928755, "count": 1, "is_parallel": true, "self": 0.046720806999928755 }, "steps_from_proto": { "total": 0.0018813490000866295, "count": 1, "is_parallel": true, "self": 0.00035994600011690636, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015214029999697232, "count": 8, "is_parallel": true, "self": 0.0015214029999697232 } } } } } } }, "UnityEnvironment.step": { "total": 1217.9720886209661, "count": 63521, "is_parallel": true, "self": 32.661821609072376, "children": { "UnityEnvironment._generate_step_input": { "total": 22.171105177044865, "count": 63521, "is_parallel": true, "self": 22.171105177044865 }, "communicator.exchange": { "total": 1063.531426569984, "count": 63521, "is_parallel": true, "self": 1063.531426569984 }, "steps_from_proto": { "total": 99.60773526486491, "count": 63521, "is_parallel": true, "self": 19.850478812032634, "children": { "_process_rank_one_or_two_observation": { "total": 79.75725645283228, "count": 508168, "is_parallel": true, "self": 79.75725645283228 } } } } } } } } } } }, "trainer_advance": { "total": 635.4343004159541, "count": 63522, "self": 2.635745420990588, "children": { "process_trajectory": { "total": 107.14197956496446, "count": 63522, "self": 106.88273633696463, "children": { "RLTrainer._checkpoint": { "total": 0.259243227999832, "count": 2, "self": 0.259243227999832 } } }, "_update_policy": { "total": 525.6565754299991, "count": 450, "self": 336.4745558229765, "children": { "TorchPPOOptimizer.update": { "total": 189.18201960702254, "count": 22722, "self": 189.18201960702254 } } } } } } }, "trainer_threads": { "total": 1.2340005923761055e-06, "count": 1, "self": 1.2340005923761055e-06 }, "TrainerController._save_models": { "total": 0.14499016699937783, "count": 1, "self": 0.0018558549991212203, "children": { "RLTrainer._checkpoint": { "total": 0.1431343120002566, "count": 1, "self": 0.1431343120002566 } } } } } } }