{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3287721574306488, "min": 0.3193697929382324, "max": 1.457699179649353, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9842.123046875, "min": 9540.21484375, "max": 44220.76171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6349695324897766, "min": -0.1380254328250885, "max": 0.6354854106903076, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 180.96630859375, "min": -32.71202850341797, "max": 181.7488250732422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026112502440810204, "min": -0.024325113743543625, "max": 0.3580947518348694, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.442063331604004, "min": -6.275879383087158, "max": 84.86845397949219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07028699548599045, "min": 0.06581948579458698, "max": 0.0736776296849834, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9840179368038662, "min": 0.498060778671897, "max": 1.0314868155897676, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018089213982290988, "min": 0.0005531157756742555, "max": 0.018776497814022675, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2532489957520738, "min": 0.00608427353241681, "max": 0.26287096939631743, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.392761821492855e-06, "min": 7.392761821492855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010349866550089997, "min": 0.00010349866550089997, "max": 0.0032237872254043, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246422142857145, "min": 0.10246422142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344991000000002, "min": 1.3886848, "max": 2.4430175000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025617572071428565, "min": 0.00025617572071428565, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003586460089999999, "min": 0.003586460089999999, "max": 0.10747211043, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007138479501008987, "min": 0.007138479501008987, "max": 0.33906790614128113, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09993871301412582, "min": 0.09993871301412582, "max": 2.3734753131866455, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.1326530612245, "min": 294.1326530612245, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28825.0, "min": 15984.0, "max": 32824.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6650346736518704, "min": -1.0000000521540642, "max": 1.6777353298784508, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.1733980178833, "min": -30.643401712179184, "max": 175.92899769544601, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6650346736518704, "min": -1.0000000521540642, "max": 1.6777353298784508, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.1733980178833, "min": -30.643401712179184, "max": 175.92899769544601, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0215718733035123, "min": 0.0215718733035123, "max": 6.714136488735676, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1140435837442055, "min": 2.1140435837442055, "max": 107.42618381977081, "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": "1742800071", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742802547" }, "total": 2476.428709829, "count": 1, "self": 0.676707312000417, "children": { "run_training.setup": { "total": 0.02005789199984065, "count": 1, "self": 0.02005789199984065 }, "TrainerController.start_learning": { "total": 2475.731944625, "count": 1, "self": 1.5116897870234425, "children": { "TrainerController._reset_env": { "total": 2.189857311999731, "count": 1, "self": 2.189857311999731 }, "TrainerController.advance": { "total": 2471.9388140059773, "count": 64107, "self": 1.6433985848461816, "children": { "env_step": { "total": 1749.5672737680597, "count": 64107, "self": 1579.7207315889082, "children": { "SubprocessEnvManager._take_step": { "total": 168.94643320802334, "count": 64107, "self": 5.0225451780343064, "children": { "TorchPolicy.evaluate": { "total": 163.92388802998903, "count": 62554, "self": 163.92388802998903 } } }, "workers": { "total": 0.9001089711282475, "count": 64107, "self": 0.0, "children": { "worker_root": { "total": 2469.9943806990022, "count": 64107, "is_parallel": true, "self": 1016.179398908947, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020119809996685944, "count": 1, "is_parallel": true, "self": 0.0006525089997921896, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013594719998764049, "count": 8, "is_parallel": true, "self": 0.0013594719998764049 } } }, "UnityEnvironment.step": { "total": 0.05249458099979165, "count": 1, "is_parallel": true, "self": 0.0005743879996771284, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004631199999494129, "count": 1, "is_parallel": true, "self": 0.0004631199999494129 }, "communicator.exchange": { "total": 0.04976121400022748, "count": 1, "is_parallel": true, "self": 0.04976121400022748 }, "steps_from_proto": { "total": 0.0016958589999376272, "count": 1, "is_parallel": true, "self": 0.0003607539993026876, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013351050006349396, "count": 8, "is_parallel": true, "self": 0.0013351050006349396 } } } } } } }, "UnityEnvironment.step": { "total": 1453.8149817900553, "count": 64106, "is_parallel": true, "self": 33.848230649151446, "children": { "UnityEnvironment._generate_step_input": { "total": 24.72019182904114, "count": 64106, "is_parallel": true, "self": 24.72019182904114 }, "communicator.exchange": { "total": 1290.9650760229833, "count": 64106, "is_parallel": true, "self": 1290.9650760229833 }, "steps_from_proto": { "total": 104.28148328887937, "count": 64106, "is_parallel": true, "self": 21.625036735092635, "children": { "_process_rank_one_or_two_observation": { "total": 82.65644655378674, "count": 512848, "is_parallel": true, "self": 82.65644655378674 } } } } } } } } } } }, "trainer_advance": { "total": 720.7281416530714, "count": 64107, "self": 2.9053027309660138, "children": { "process_trajectory": { "total": 141.60361290210676, "count": 64107, "self": 141.37621644210776, "children": { "RLTrainer._checkpoint": { "total": 0.2273964599989995, "count": 2, "self": 0.2273964599989995 } } }, "_update_policy": { "total": 576.2192260199986, "count": 446, "self": 319.0857988020243, "children": { "TorchPPOOptimizer.update": { "total": 257.13342721797426, "count": 22839, "self": 257.13342721797426 } } } } } } }, "trainer_threads": { "total": 9.93999492493458e-07, "count": 1, "self": 9.93999492493458e-07 }, "TrainerController._save_models": { "total": 0.09158252599991101, "count": 1, "self": 0.0016028089994506445, "children": { "RLTrainer._checkpoint": { "total": 0.08997971700046037, "count": 1, "self": 0.08997971700046037 } } } } } } }