{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44343188405036926, "min": 0.4422524571418762, "max": 1.4796161651611328, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13288.7666015625, "min": 13288.7666015625, "max": 44885.63671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.555169403553009, "min": -0.07640481740236282, "max": 0.6166432499885559, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.78192138671875, "min": -18.41356086730957, "max": 172.04347229003906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003325456753373146, "min": 0.003318789880722761, "max": 0.37097224593162537, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.9211515188217163, "min": 0.8562477827072144, "max": 89.77528381347656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0668359316824492, "min": 0.06574777701396935, "max": 0.07347759801373654, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9357030435542887, "min": 0.49014574319362403, "max": 1.0613277813536115, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01786354147216549, "min": 0.00043779097343768253, "max": 0.018623049995943143, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2500895806103169, "min": 0.006129073628127556, "max": 0.260722699943204, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.743268847514289e-06, "min": 7.743268847514289e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010840576386520005, "min": 0.00010840576386520005, "max": 0.003758353947215399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258105714285715, "min": 0.10258105714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361348, "min": 1.3886848, "max": 2.6527846, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026784760857142864, "min": 0.00026784760857142864, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003749866520000001, "min": 0.003749866520000001, "max": 0.12529318154, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013201264664530754, "min": 0.013201264664530754, "max": 0.6614483594894409, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18481770157814026, "min": 0.18481770157814026, "max": 4.630138397216797, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.3723404255319, "min": 301.5050505050505, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30867.0, "min": 15984.0, "max": 33429.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6077744463022718, "min": -1.0000000521540642, "max": 1.6984949309115458, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 151.13079795241356, "min": -31.994001656770706, "max": 168.15099816024303, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6077744463022718, "min": -1.0000000521540642, "max": 1.6984949309115458, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 151.13079795241356, "min": -31.994001656770706, "max": 168.15099816024303, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04497627533992079, "min": 0.04294012762392128, "max": 13.38169926777482, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.227769881952554, "min": 4.147454440855654, "max": 214.10718828439713, "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": "1735310534", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735313385" }, "total": 2851.58034099, "count": 1, "self": 0.9401706570001807, "children": { "run_training.setup": { "total": 0.06219426799998473, "count": 1, "self": 0.06219426799998473 }, "TrainerController.start_learning": { "total": 2850.577976065, "count": 1, "self": 2.1806132560623155, "children": { "TrainerController._reset_env": { "total": 5.320990028999859, "count": 1, "self": 5.320990028999859 }, "TrainerController.advance": { "total": 2842.9209085529383, "count": 64096, "self": 2.211332235905502, "children": { "env_step": { "total": 2046.3581528619643, "count": 64096, "self": 1843.4711954629634, "children": { "SubprocessEnvManager._take_step": { "total": 201.61193134709902, "count": 64096, "self": 6.166418657134045, "children": { "TorchPolicy.evaluate": { "total": 195.44551268996497, "count": 62571, "self": 195.44551268996497 } } }, "workers": { "total": 1.275026051901932, "count": 64096, "self": 0.0, "children": { "worker_root": { "total": 2842.967168274056, "count": 64096, "is_parallel": true, "self": 1160.7467036160197, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021826160000273376, "count": 1, "is_parallel": true, "self": 0.0007506369997827278, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014319790002446098, "count": 8, "is_parallel": true, "self": 0.0014319790002446098 } } }, "UnityEnvironment.step": { "total": 0.05516294500012009, "count": 1, "is_parallel": true, "self": 0.0006724070003656379, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005204669998875033, "count": 1, "is_parallel": true, "self": 0.0005204669998875033 }, "communicator.exchange": { "total": 0.05203671799995391, "count": 1, "is_parallel": true, "self": 0.05203671799995391 }, "steps_from_proto": { "total": 0.0019333529999130405, "count": 1, "is_parallel": true, "self": 0.00042569499964884017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015076580002642004, "count": 8, "is_parallel": true, "self": 0.0015076580002642004 } } } } } } }, "UnityEnvironment.step": { "total": 1682.2204646580362, "count": 64095, "is_parallel": true, "self": 43.855330336063844, "children": { "UnityEnvironment._generate_step_input": { "total": 27.887135275969513, "count": 64095, "is_parallel": true, "self": 27.887135275969513 }, "communicator.exchange": { "total": 1486.7428550810037, "count": 64095, "is_parallel": true, "self": 1486.7428550810037 }, "steps_from_proto": { "total": 123.73514396499922, "count": 64095, "is_parallel": true, "self": 26.864576416306818, "children": { "_process_rank_one_or_two_observation": { "total": 96.8705675486924, "count": 512760, "is_parallel": true, "self": 96.8705675486924 } } } } } } } } } } }, "trainer_advance": { "total": 794.3514234550685, "count": 64096, "self": 4.014514773070232, "children": { "process_trajectory": { "total": 163.35734097599834, "count": 64096, "self": 163.0260445359986, "children": { "RLTrainer._checkpoint": { "total": 0.3312964399997327, "count": 2, "self": 0.3312964399997327 } } }, "_update_policy": { "total": 626.9795677059999, "count": 458, "self": 351.5291690409997, "children": { "TorchPPOOptimizer.update": { "total": 275.4503986650002, "count": 22767, "self": 275.4503986650002 } } } } } } }, "trainer_threads": { "total": 1.880000127130188e-06, "count": 1, "self": 1.880000127130188e-06 }, "TrainerController._save_models": { "total": 0.15546234699922934, "count": 1, "self": 0.0025254949987356667, "children": { "RLTrainer._checkpoint": { "total": 0.15293685200049367, "count": 1, "self": 0.15293685200049367 } } } } } } }