{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6366907954216003, "min": 0.6326351165771484, "max": 1.4710193872451782, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19039.6015625, "min": 19039.6015625, "max": 44624.84375, "count": 33 }, "Pyramids.Step.mean": { "value": 989895.0, "min": 29952.0, "max": 989895.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989895.0, "min": 29952.0, "max": 989895.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.25526097416877747, "min": -0.10244600474834442, "max": 0.3214500844478607, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 65.09154510498047, "min": -24.68948745727539, "max": 82.93412017822266, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07153212279081345, "min": -0.012669753283262253, "max": 0.3484809994697571, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.240692138671875, "min": -3.268796443939209, "max": 82.58999633789062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06698762103991847, "min": 0.06593401564353746, "max": 0.07334028164848871, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9378266945588586, "min": 0.4672153268424906, "max": 1.0496439071270574, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012222873695502146, "min": 0.00017645008476284, "max": 0.013067163493057404, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17112023173703003, "min": 0.0022192602048813443, "max": 0.19475511848577298, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.39852610528571e-06, "min": 7.39852610528571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010357936547399993, "min": 0.00010357936547399993, "max": 0.0029040510319831, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246614285714287, "min": 0.10246614285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345260000000002, "min": 1.327104, "max": 2.3168824, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025636767142857124, "min": 0.00025636767142857124, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035891473999999975, "min": 0.0035891473999999975, "max": 0.09683488830999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01259760744869709, "min": 0.01259760744869709, "max": 0.3874432146549225, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17636650800704956, "min": 0.17636650800704956, "max": 2.7121024131774902, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 598.2244897959183, "min": 534.94, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29313.0, "min": 15984.0, "max": 34028.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9527020065151915, "min": -1.0000000521540642, "max": 1.1849719701707364, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 46.682398319244385, "min": -32.000001668930054, "max": 65.38219823688269, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9527020065151915, "min": -1.0000000521540642, "max": 1.1849719701707364, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 46.682398319244385, "min": -32.000001668930054, "max": 65.38219823688269, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07879846870699632, "min": 0.072107994282851, "max": 7.790339522995055, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8611249666428193, "min": 3.60539971414255, "max": 124.64543236792088, "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": "1749122723", "python_version": "3.10.12 (main, May 22 2025, 18:49:42) [GCC 9.4.0]", "command_line_arguments": "/root/.pyenv/versions/3.10.12/envs/mlagents-env/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": "1749123453" }, "total": 729.8992273199838, "count": 1, "self": 0.16776729398407042, "children": { "run_training.setup": { "total": 0.015211247955448925, "count": 1, "self": 0.015211247955448925 }, "TrainerController.start_learning": { "total": 729.7162487780442, "count": 1, "self": 0.5489939770195633, "children": { "TrainerController._reset_env": { "total": 1.2213104009861127, "count": 1, "self": 1.2213104009861127 }, "TrainerController.advance": { "total": 727.875729820109, "count": 63263, "self": 0.5116539106238633, "children": { "env_step": { "total": 419.04043401032686, "count": 63263, "self": 359.5443633766845, "children": { "SubprocessEnvManager._take_step": { "total": 59.139376597478986, "count": 63263, "self": 1.8155213001882657, "children": { "TorchPolicy.evaluate": { "total": 57.32385529729072, "count": 62558, "self": 57.32385529729072 } } }, "workers": { "total": 0.3566940361633897, "count": 63263, "self": 0.0, "children": { "worker_root": { "total": 728.8358508822275, "count": 63263, "is_parallel": true, "self": 408.0505331553286, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011919280514121056, "count": 1, "is_parallel": true, "self": 0.0003153699217364192, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008765581296756864, "count": 8, "is_parallel": true, "self": 0.0008765581296756864 } } }, "UnityEnvironment.step": { "total": 0.014684502966701984, "count": 1, "is_parallel": true, "self": 0.00013135606423020363, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016578997019678354, "count": 1, "is_parallel": true, "self": 0.00016578997019678354 }, "communicator.exchange": { "total": 0.013947013998404145, "count": 1, "is_parallel": true, "self": 0.013947013998404145 }, "steps_from_proto": { "total": 0.000440342933870852, "count": 1, "is_parallel": true, "self": 0.00011376070324331522, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003265822306275368, "count": 8, "is_parallel": true, "self": 0.0003265822306275368 } } } } } } }, "UnityEnvironment.step": { "total": 320.78531772689894, "count": 63262, "is_parallel": true, "self": 7.6567263077013195, "children": { "UnityEnvironment._generate_step_input": { "total": 6.2820627798791975, "count": 63262, "is_parallel": true, "self": 6.2820627798791975 }, "communicator.exchange": { "total": 282.8848052180838, "count": 63262, "is_parallel": true, "self": 282.8848052180838 }, "steps_from_proto": { "total": 23.961723421234637, "count": 63262, "is_parallel": true, "self": 5.070053078816272, "children": { "_process_rank_one_or_two_observation": { "total": 18.891670342418365, "count": 506096, "is_parallel": true, "self": 18.891670342418365 } } } } } } } } } } }, "trainer_advance": { "total": 308.32364189915825, "count": 63263, "self": 0.9477613372728229, "children": { "process_trajectory": { "total": 62.47097094345372, "count": 63263, "self": 62.32406992139295, "children": { "RLTrainer._checkpoint": { "total": 0.14690102206077427, "count": 2, "self": 0.14690102206077427 } } }, "_update_policy": { "total": 244.9049096184317, "count": 426, "self": 151.7253253060626, "children": { "TorchPPOOptimizer.update": { "total": 93.17958431236912, "count": 22899, "self": 93.17958431236912 } } } } } } }, "trainer_threads": { "total": 6.009358912706375e-07, "count": 1, "self": 6.009358912706375e-07 }, "TrainerController._save_models": { "total": 0.0702139789937064, "count": 1, "self": 0.0008898619562387466, "children": { "RLTrainer._checkpoint": { "total": 0.06932411703746766, "count": 1, "self": 0.06932411703746766 } } } } } } }