{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20138226449489594, "min": 0.20138226449489594, "max": 1.540317416191101, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 6047.912109375, "min": 6047.912109375, "max": 46727.0703125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999920.0, "min": 29952.0, "max": 2999920.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999920.0, "min": 29952.0, "max": 2999920.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7609947919845581, "min": -0.13127391040325165, "max": 0.8544310331344604, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 222.9714813232422, "min": -31.11191749572754, "max": 255.47488403320312, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01954497955739498, "min": -0.03343815729022026, "max": 0.35426273941993713, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.726678848266602, "min": -8.392977714538574, "max": 83.96026611328125, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06648473991247426, "min": 0.06249564615496812, "max": 0.07316022558598871, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9307863587746397, "min": 0.4984539879555212, "max": 1.084052477457661, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01189694404560474, "min": 7.992197370520794e-05, "max": 0.01567412942642391, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16655721663846637, "min": 0.0011189076318729111, "max": 0.2194378119699347, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4359638070928602e-06, "min": 1.4359638070928602e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0103493299300043e-05, "min": 2.0103493299300043e-05, "max": 0.003927402790865767, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047862142857143, "min": 0.10047862142857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067007, "min": 1.3962282666666668, "max": 2.7225485666666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.781428071428582e-05, "min": 5.781428071428582e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008093999300000015, "min": 0.0008093999300000015, "max": 0.13092250991, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00474893394857645, "min": 0.004502505529671907, "max": 0.3025861084461212, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06648507714271545, "min": 0.06338441371917725, "max": 2.118102788925171, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 237.1382113821138, "min": 210.14685314685315, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29168.0, "min": 15984.0, "max": 32672.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7140633997514965, "min": -1.0000000521540642, "max": 1.7799565059983211, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 210.82979816943407, "min": -31.988401636481285, "max": 253.94839818775654, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7140633997514965, "min": -1.0000000521540642, "max": 1.7799565059983211, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 210.82979816943407, "min": -31.988401636481285, "max": 253.94839818775654, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011723713378574106, "min": 0.010626069764734037, "max": 6.4212075704708695, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4420167455646151, "min": 1.3784741695853882, "max": 102.73932112753391, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1750397537", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750404615" }, "total": 7078.558162544001, "count": 1, "self": 0.8425796990013623, "children": { "run_training.setup": { "total": 0.020924662000197713, "count": 1, "self": 0.020924662000197713 }, "TrainerController.start_learning": { "total": 7077.694658183, "count": 1, "self": 4.367864426154483, "children": { "TrainerController._reset_env": { "total": 2.5128700870000102, "count": 1, "self": 2.5128700870000102 }, "TrainerController.advance": { "total": 7070.688419566845, "count": 194286, "self": 4.563008552135216, "children": { "env_step": { "total": 5096.796377944769, "count": 194286, "self": 4632.686227774006, "children": { "SubprocessEnvManager._take_step": { "total": 461.41533695088265, "count": 194286, "self": 14.039096691838495, "children": { "TorchPolicy.evaluate": { "total": 447.37624025904415, "count": 187556, "self": 447.37624025904415 } } }, "workers": { "total": 2.6948132198808707, "count": 194286, "self": 0.0, "children": { "worker_root": { "total": 7061.327090915078, "count": 194286, "is_parallel": true, "self": 2779.2812997570672, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018087570001625863, "count": 1, "is_parallel": true, "self": 0.0005812520003019017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012275049998606846, "count": 8, "is_parallel": true, "self": 0.0012275049998606846 } } }, "UnityEnvironment.step": { "total": 0.08920139700012442, "count": 1, "is_parallel": true, "self": 0.000511482000547403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004670669995903154, "count": 1, "is_parallel": true, "self": 0.0004670669995903154 }, "communicator.exchange": { "total": 0.08669450799970946, "count": 1, "is_parallel": true, "self": 0.08669450799970946 }, "steps_from_proto": { "total": 0.0015283400002772396, "count": 1, "is_parallel": true, "self": 0.00031481899986829376, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012135210004089458, "count": 8, "is_parallel": true, "self": 0.0012135210004089458 } } } } } } }, "UnityEnvironment.step": { "total": 4282.045791158011, "count": 194285, "is_parallel": true, "self": 96.94194578005954, "children": { "UnityEnvironment._generate_step_input": { "total": 68.62730982311996, "count": 194285, "is_parallel": true, "self": 68.62730982311996 }, "communicator.exchange": { "total": 3822.7236126539588, "count": 194285, "is_parallel": true, "self": 3822.7236126539588 }, "steps_from_proto": { "total": 293.7529229008728, "count": 194285, "is_parallel": true, "self": 60.63405398377017, "children": { "_process_rank_one_or_two_observation": { "total": 233.11886891710265, "count": 1554280, "is_parallel": true, "self": 233.11886891710265 } } } } } } } } } } }, "trainer_advance": { "total": 1969.329033069941, "count": 194286, "self": 8.907460543970501, "children": { "process_trajectory": { "total": 381.48934369397057, "count": 194286, "self": 380.76507286397054, "children": { "RLTrainer._checkpoint": { "total": 0.7242708300000231, "count": 6, "self": 0.7242708300000231 } } }, "_update_policy": { "total": 1578.932228832, "count": 1395, "self": 872.2222648069455, "children": { "TorchPPOOptimizer.update": { "total": 706.7099640250544, "count": 68391, "self": 706.7099640250544 } } } } } } }, "trainer_threads": { "total": 1.276999682886526e-06, "count": 1, "self": 1.276999682886526e-06 }, "TrainerController._save_models": { "total": 0.1255028260002291, "count": 1, "self": 0.0018837570005416637, "children": { "RLTrainer._checkpoint": { "total": 0.12361906899968744, "count": 1, "self": 0.12361906899968744 } } } } } } }