{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4003141224384308, "min": 0.39134469628334045, "max": 1.4944818019866943, "count": 32 }, "Pyramids.Policy.Entropy.sum": { "value": 11977.3984375, "min": 11652.6796875, "max": 45336.6015625, "count": 32 }, "Pyramids.Step.mean": { "value": 959935.0, "min": 29947.0, "max": 959935.0, "count": 32 }, "Pyramids.Step.sum": { "value": 959935.0, "min": 29947.0, "max": 959935.0, "count": 32 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5146921277046204, "min": -0.08552314341068268, "max": 0.574161171913147, "count": 32 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 140.51095581054688, "min": -20.6110782623291, "max": 158.46847534179688, "count": 32 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04151313379406929, "min": 0.0020496181678026915, "max": 0.2596645951271057, "count": 32 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.333085060119629, "min": 0.5492976903915405, "max": 62.57917022705078, "count": 32 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0687998960400196, "min": 0.0654457644291041, "max": 0.07439856213334549, "count": 32 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9631985445602743, "min": 0.488584716004472, "max": 1.0575224384796742, "count": 32 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012694516616889912, "min": 0.000668431320429157, "max": 0.014908696715359661, "count": 32 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17772323263645876, "min": 0.00868960716557904, "max": 0.20872175401503526, "count": 32 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.6462530226807145e-05, "min": 1.6462530226807145e-05, "max": 0.0002952331301603857, "count": 32 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002304754231753, "min": 0.0002304754231753, "max": 0.0037577932474022993, "count": 32 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10548747857142858, "min": 0.10548747857142858, "max": 0.19841104285714284, "count": 32 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4768247, "min": 1.3888772999999999, "max": 2.6525977, "count": 32 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005581991092857145, "min": 0.0005581991092857145, "max": 0.009841263181428571, "count": 32 }, "Pyramids.Policy.Beta.sum": { "value": 0.007814787530000002, "min": 0.007814787530000002, "max": 0.12527451023, "count": 32 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010585588403046131, "min": 0.010585588403046131, "max": 0.3223348557949066, "count": 32 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1481982320547104, "min": 0.1481982320547104, "max": 2.2563440799713135, "count": 32 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 399.72972972972974, "min": 332.7261904761905, "max": 987.09375, "count": 32 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29580.0, "min": 16746.0, "max": 33200.0, "count": 32 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.51915402831258, "min": -0.9162387614769321, "max": 1.668447045192999, "count": 32 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.41739809513092, "min": -29.231601782143116, "max": 141.81799884140491, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.51915402831258, "min": -0.9162387614769321, "max": 1.668447045192999, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.41739809513092, "min": -29.231601782143116, "max": 141.81799884140491, "count": 32 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04313082571555955, "min": 0.037625356123317036, "max": 5.517900224117672, "count": 32 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1916811029514065, "min": 3.1916811029514065, "max": 93.80430381000042, "count": 32 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 32 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1722328040", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722330167" }, "total": 2127.1229638229997, "count": 1, "self": 0.3384459919998335, "children": { "run_training.setup": { "total": 0.08648732199981168, "count": 1, "self": 0.08648732199981168 }, "TrainerController.start_learning": { "total": 2126.698030509, "count": 1, "self": 1.3824298700274085, "children": { "TrainerController._reset_env": { "total": 2.104344175000051, "count": 1, "self": 2.104344175000051 }, "TrainerController.advance": { "total": 2123.0780259039725, "count": 62872, "self": 1.465674241945635, "children": { "env_step": { "total": 1487.5903162240309, "count": 62872, "self": 1356.8307889290043, "children": { "SubprocessEnvManager._take_step": { "total": 129.91240819697305, "count": 62872, "self": 4.8686691249797605, "children": { "TorchPolicy.evaluate": { "total": 125.04373907199329, "count": 61645, "self": 125.04373907199329 } } }, "workers": { "total": 0.8471190980535539, "count": 62871, "self": 0.0, "children": { "worker_root": { "total": 2121.5744823409455, "count": 62871, "is_parallel": true, "self": 886.1328977869491, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021165709999877436, "count": 1, "is_parallel": true, "self": 0.0006889689998388349, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014276020001489087, "count": 8, "is_parallel": true, "self": 0.0014276020001489087 } } }, "UnityEnvironment.step": { "total": 0.05638080100015941, "count": 1, "is_parallel": true, "self": 0.0007150040003125469, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005104289998598688, "count": 1, "is_parallel": true, "self": 0.0005104289998598688 }, "communicator.exchange": { "total": 0.05330223400005707, "count": 1, "is_parallel": true, "self": 0.05330223400005707 }, "steps_from_proto": { "total": 0.0018531339999299234, "count": 1, "is_parallel": true, "self": 0.00040642799990564527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014467060000242782, "count": 8, "is_parallel": true, "self": 0.0014467060000242782 } } } } } } }, "UnityEnvironment.step": { "total": 1235.4415845539963, "count": 62870, "is_parallel": true, "self": 33.16189835814589, "children": { "UnityEnvironment._generate_step_input": { "total": 24.02163148696195, "count": 62870, "is_parallel": true, "self": 24.02163148696195 }, "communicator.exchange": { "total": 1079.1638750779568, "count": 62870, "is_parallel": true, "self": 1079.1638750779568 }, "steps_from_proto": { "total": 99.09417963093165, "count": 62870, "is_parallel": true, "self": 20.39782680286021, "children": { "_process_rank_one_or_two_observation": { "total": 78.69635282807144, "count": 502960, "is_parallel": true, "self": 78.69635282807144 } } } } } } } } } } }, "trainer_advance": { "total": 634.022035437996, "count": 62871, "self": 2.696731340970018, "children": { "process_trajectory": { "total": 129.84177630302747, "count": 62871, "self": 129.7303246500278, "children": { "RLTrainer._checkpoint": { "total": 0.1114516529996763, "count": 1, "self": 0.1114516529996763 } } }, "_update_policy": { "total": 501.4835277939985, "count": 451, "self": 298.26667327698874, "children": { "TorchPPOOptimizer.update": { "total": 203.21685451700978, "count": 22485, "self": 203.21685451700978 } } } } } } }, "trainer_threads": { "total": 1.5489999896090012e-06, "count": 1, "self": 1.5489999896090012e-06 }, "TrainerController._save_models": { "total": 0.13322901099991213, "count": 1, "self": 0.00199322900016341, "children": { "RLTrainer._checkpoint": { "total": 0.13123578199974872, "count": 1, "self": 0.13123578199974872 } } } } } } }