{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43619248270988464, "min": 0.43619248270988464, "max": 1.4520533084869385, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13239.314453125, "min": 13239.314453125, "max": 44049.48828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.14326219260692596, "min": -0.12083493918180466, "max": 0.18571296334266663, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 35.529022216796875, "min": -29.121219635009766, "max": 47.17109298706055, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027769923210144043, "min": 0.015405929647386074, "max": 0.5684710144996643, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.886940956115723, "min": 3.743640899658203, "max": 134.72763061523438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07137393387885967, "min": 0.06533262936839591, "max": 0.07363117916134393, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9992350743040354, "min": 0.4770290960628678, "max": 1.1044676874201589, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009305816587864795, "min": 0.0010180396564200662, "max": 0.01850194055816085, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13028143223010713, "min": 0.011105572171099889, "max": 0.17425681570874113, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.427090381478569e-06, "min": 7.427090381478569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010397926534069996, "min": 0.00010397926534069996, "max": 0.0035073905308698997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247566428571428, "min": 0.10247566428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346592999999999, "min": 1.3691136000000002, "max": 2.5691301, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002573188621428571, "min": 0.0002573188621428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036024640699999994, "min": 0.0036024640699999994, "max": 0.11693609699000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01684480719268322, "min": 0.01684480719268322, "max": 0.6035431623458862, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23582731187343597, "min": 0.23582731187343597, "max": 4.224802017211914, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 715.1052631578947, "min": 650.58, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27174.0, "min": 15984.0, "max": 32529.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5197351025165738, "min": -1.0000000521540642, "max": 0.844234118919547, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 19.23019879311323, "min": -32.000001668930054, "max": 34.61359887570143, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5197351025165738, "min": -1.0000000521540642, "max": 0.844234118919547, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 19.23019879311323, "min": -32.000001668930054, "max": 34.61359887570143, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1270365567399642, "min": 0.11415854611434043, "max": 12.884078552946448, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.700352599378675, "min": 4.700352599378675, "max": 206.14525684714317, "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": "1764036507", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1764038597" }, "total": 2089.6059063190005, "count": 1, "self": 0.4775345130005917, "children": { "run_training.setup": { "total": 0.02319891999968604, "count": 1, "self": 0.02319891999968604 }, "TrainerController.start_learning": { "total": 2089.105172886, "count": 1, "self": 1.4078762900430775, "children": { "TrainerController._reset_env": { "total": 2.0119572559997323, "count": 1, "self": 2.0119572559997323 }, "TrainerController.advance": { "total": 2085.6093560669583, "count": 63336, "self": 1.499776870122787, "children": { "env_step": { "total": 1430.2468238299302, "count": 63336, "self": 1275.5251404809578, "children": { "SubprocessEnvManager._take_step": { "total": 153.8734406499957, "count": 63336, "self": 4.626334661030796, "children": { "TorchPolicy.evaluate": { "total": 149.2471059889649, "count": 62577, "self": 149.2471059889649 } } }, "workers": { "total": 0.8482426989767191, "count": 63336, "self": 0.0, "children": { "worker_root": { "total": 2082.5258967409936, "count": 63336, "is_parallel": true, "self": 925.778975602092, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018667859999368375, "count": 1, "is_parallel": true, "self": 0.0005955330002507253, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012712529996861122, "count": 8, "is_parallel": true, "self": 0.0012712529996861122 } } }, "UnityEnvironment.step": { "total": 0.04726257299989811, "count": 1, "is_parallel": true, "self": 0.0005651699993904913, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047712000014143996, "count": 1, "is_parallel": true, "self": 0.00047712000014143996 }, "communicator.exchange": { "total": 0.04451461600001494, "count": 1, "is_parallel": true, "self": 0.04451461600001494 }, "steps_from_proto": { "total": 0.0017056670003512409, "count": 1, "is_parallel": true, "self": 0.000362816001597821, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013428509987534198, "count": 8, "is_parallel": true, "self": 0.0013428509987534198 } } } } } } }, "UnityEnvironment.step": { "total": 1156.7469211389016, "count": 63335, "is_parallel": true, "self": 33.7487428308973, "children": { "UnityEnvironment._generate_step_input": { "total": 23.68552457414353, "count": 63335, "is_parallel": true, "self": 23.68552457414353 }, "communicator.exchange": { "total": 989.7077681439832, "count": 63335, "is_parallel": true, "self": 989.7077681439832 }, "steps_from_proto": { "total": 109.60488558987754, "count": 63335, "is_parallel": true, "self": 23.048047569910977, "children": { "_process_rank_one_or_two_observation": { "total": 86.55683801996656, "count": 506680, "is_parallel": true, "self": 86.55683801996656 } } } } } } } } } } }, "trainer_advance": { "total": 653.8627553669053, "count": 63336, "self": 2.7058591068839632, "children": { "process_trajectory": { "total": 124.38750293001567, "count": 63336, "self": 124.20568530001538, "children": { "RLTrainer._checkpoint": { "total": 0.18181763000029605, "count": 2, "self": 0.18181763000029605 } } }, "_update_policy": { "total": 526.7693933300056, "count": 445, "self": 291.5442858189581, "children": { "TorchPPOOptimizer.update": { "total": 235.22510751104755, "count": 22824, "self": 235.22510751104755 } } } } } } }, "trainer_threads": { "total": 9.839995982474647e-07, "count": 1, "self": 9.839995982474647e-07 }, "TrainerController._save_models": { "total": 0.0759822889995121, "count": 1, "self": 0.0009287140001106309, "children": { "RLTrainer._checkpoint": { "total": 0.07505357499940146, "count": 1, "self": 0.07505357499940146 } } } } } } }