{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3451898396015167, "min": 0.32278311252593994, "max": 1.4672908782958984, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10355.6953125, "min": 9657.6708984375, "max": 44511.734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4771062135696411, "min": -0.11603613942861557, "max": 0.4967271089553833, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.77288818359375, "min": -27.964710235595703, "max": 135.10977172851562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04895235225558281, "min": 0.003913287539035082, "max": 0.17591160535812378, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.31503963470459, "min": 1.0135414600372314, "max": 42.21878433227539, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06769489382471268, "min": 0.06619044014989259, "max": 0.07513319019697322, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9477285135459775, "min": 0.49231849053483884, "max": 1.0431050295729247, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016289081336816752, "min": 0.00011372251574576096, "max": 0.016289081336816752, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22804713871543453, "min": 0.0014783927046948925, "max": 0.22804713871543453, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.747961703092852e-06, "min": 7.747961703092852e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010847146384329992, "min": 0.00010847146384329992, "max": 0.0035071082309639998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258262142857144, "min": 0.10258262142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361567000000002, "min": 1.3691136000000002, "max": 2.569036, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002680038807142855, "min": 0.0002680038807142855, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037520543299999973, "min": 0.0037520543299999973, "max": 0.11692669639999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010832734405994415, "min": 0.010832734405994415, "max": 0.34413108229637146, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15165828168392181, "min": 0.15165828168392181, "max": 2.4089176654815674, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 413.1818181818182, "min": 351.49367088607596, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31815.0, "min": 15984.0, "max": 32878.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.48288308567815, "min": -1.0000000521540642, "max": 1.5472202368929415, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.18199759721756, "min": -32.000001668930054, "max": 122.23039871454239, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.48288308567815, "min": -1.0000000521540642, "max": 1.5472202368929415, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.18199759721756, "min": -32.000001668930054, "max": 122.23039871454239, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.046353139268429405, "min": 0.04352635219825809, "max": 6.731055837124586, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5691917236690642, "min": 3.438581823662389, "max": 107.69689339399338, "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": "1684704807", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "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": "1684706900" }, "total": 2092.82354672, "count": 1, "self": 0.6742174259998137, "children": { "run_training.setup": { "total": 0.036505916000351135, "count": 1, "self": 0.036505916000351135 }, "TrainerController.start_learning": { "total": 2092.112823378, "count": 1, "self": 1.451754589948905, "children": { "TrainerController._reset_env": { "total": 3.9812919500000135, "count": 1, "self": 3.9812919500000135 }, "TrainerController.advance": { "total": 2086.5893430780507, "count": 63570, "self": 1.3879085690314241, "children": { "env_step": { "total": 1469.8193728879878, "count": 63570, "self": 1360.6257927877432, "children": { "SubprocessEnvManager._take_step": { "total": 108.36934428110726, "count": 63570, "self": 4.737380682133335, "children": { "TorchPolicy.evaluate": { "total": 103.63196359897393, "count": 62535, "self": 103.63196359897393 } } }, "workers": { "total": 0.8242358191373569, "count": 63570, "self": 0.0, "children": { "worker_root": { "total": 2087.6708071969824, "count": 63570, "is_parallel": true, "self": 837.9054963669869, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001762186000632937, "count": 1, "is_parallel": true, "self": 0.0005982349994155811, "children": { "_process_rank_one_or_two_observation": { "total": 0.001163951001217356, "count": 8, "is_parallel": true, "self": 0.001163951001217356 } } }, "UnityEnvironment.step": { "total": 0.08652751199952036, "count": 1, "is_parallel": true, "self": 0.0005228950003584032, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044911099939781707, "count": 1, "is_parallel": true, "self": 0.00044911099939781707 }, "communicator.exchange": { "total": 0.08381746899976861, "count": 1, "is_parallel": true, "self": 0.08381746899976861 }, "steps_from_proto": { "total": 0.0017380369999955292, "count": 1, "is_parallel": true, "self": 0.00035452699921734165, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013835100007781875, "count": 8, "is_parallel": true, "self": 0.0013835100007781875 } } } } } } }, "UnityEnvironment.step": { "total": 1249.7653108299955, "count": 63569, "is_parallel": true, "self": 31.042176180070783, "children": { "UnityEnvironment._generate_step_input": { "total": 22.14579778501502, "count": 63569, "is_parallel": true, "self": 22.14579778501502 }, "communicator.exchange": { "total": 1101.4700820558837, "count": 63569, "is_parallel": true, "self": 1101.4700820558837 }, "steps_from_proto": { "total": 95.10725480902602, "count": 63569, "is_parallel": true, "self": 19.34154029189449, "children": { "_process_rank_one_or_two_observation": { "total": 75.76571451713153, "count": 508552, "is_parallel": true, "self": 75.76571451713153 } } } } } } } } } } }, "trainer_advance": { "total": 615.3820616210314, "count": 63570, "self": 2.6622383820540563, "children": { "process_trajectory": { "total": 104.65530550598032, "count": 63570, "self": 104.45904291797979, "children": { "RLTrainer._checkpoint": { "total": 0.1962625880005362, "count": 2, "self": 0.1962625880005362 } } }, "_update_policy": { "total": 508.06451773299705, "count": 443, "self": 327.0830543019674, "children": { "TorchPPOOptimizer.update": { "total": 180.98146343102962, "count": 22806, "self": 180.98146343102962 } } } } } } }, "trainer_threads": { "total": 8.460001481580548e-07, "count": 1, "self": 8.460001481580548e-07 }, "TrainerController._save_models": { "total": 0.09043291400030284, "count": 1, "self": 0.0013771719995929743, "children": { "RLTrainer._checkpoint": { "total": 0.08905574200070987, "count": 1, "self": 0.08905574200070987 } } } } } } }