{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3667028248310089, "min": 0.365723580121994, "max": 1.4094637632369995, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10995.2177734375, "min": 10919.04296875, "max": 42757.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5995796918869019, "min": -0.11152351647615433, "max": 0.6032332181930542, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.4818878173828, "min": -26.988691329956055, "max": 168.90530395507812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017093468457460403, "min": -0.0575275719165802, "max": 0.41233518719673157, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.803264617919922, "min": -14.612003326416016, "max": 97.72344207763672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07039783142265929, "min": 0.06553946439131643, "max": 0.07554125596423349, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9855696399172301, "min": 0.5287887917496344, "max": 1.0637411315889787, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015082918382610108, "min": 0.0012219156017726268, "max": 0.015082918382610108, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2111608573565415, "min": 0.012219156017726268, "max": 0.22539398610630693, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.746290275078576e-06, "min": 7.746290275078576e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010844806385110007, "min": 0.00010844806385110007, "max": 0.0036330337889888, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258206428571429, "min": 0.10258206428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361489, "min": 1.3886848, "max": 2.6110111999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002679482221428573, "min": 0.0002679482221428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003751275110000002, "min": 0.003751275110000002, "max": 0.12112001888000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008729719556868076, "min": 0.008729719556868076, "max": 0.45837393403053284, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12221607565879822, "min": 0.12221607565879822, "max": 3.2086174488067627, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 330.2857142857143, "min": 316.96590909090907, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30056.0, "min": 15984.0, "max": 32569.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6231260660873807, "min": -1.0000000521540642, "max": 1.6611221969127654, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.32759808003902, "min": -30.60100167989731, "max": 149.5009977221489, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6231260660873807, "min": -1.0000000521540642, "max": 1.6611221969127654, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.32759808003902, "min": -30.60100167989731, "max": 149.5009977221489, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029990243719468075, "min": 0.029990243719468075, "max": 9.897293385118246, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.759102422191063, "min": 2.5656284043507185, "max": 158.35669416189194, "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": "1720127562", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720130121" }, "total": 2558.7142118459997, "count": 1, "self": 0.4771320690006178, "children": { "run_training.setup": { "total": 0.056145540999750665, "count": 1, "self": 0.056145540999750665 }, "TrainerController.start_learning": { "total": 2558.1809342359993, "count": 1, "self": 1.7067567641179267, "children": { "TrainerController._reset_env": { "total": 2.2889652479998404, "count": 1, "self": 2.2889652479998404 }, "TrainerController.advance": { "total": 2554.0882469238813, "count": 64042, "self": 1.707070854849917, "children": { "env_step": { "total": 1873.3137074250499, "count": 64042, "self": 1721.9574135128669, "children": { "SubprocessEnvManager._take_step": { "total": 150.33391681398643, "count": 64042, "self": 5.296353522046047, "children": { "TorchPolicy.evaluate": { "total": 145.0375632919404, "count": 62560, "self": 145.0375632919404 } } }, "workers": { "total": 1.0223770981965572, "count": 64042, "self": 0.0, "children": { "worker_root": { "total": 2551.8347460149116, "count": 64042, "is_parallel": true, "self": 971.4676296848975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002256648999718891, "count": 1, "is_parallel": true, "self": 0.0007277289996636682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015289200000552228, "count": 8, "is_parallel": true, "self": 0.0015289200000552228 } } }, "UnityEnvironment.step": { "total": 0.09825269400062098, "count": 1, "is_parallel": true, "self": 0.0006632889999309555, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004935420001856983, "count": 1, "is_parallel": true, "self": 0.0004935420001856983 }, "communicator.exchange": { "total": 0.0953380320006545, "count": 1, "is_parallel": true, "self": 0.0953380320006545 }, "steps_from_proto": { "total": 0.0017578309998498298, "count": 1, "is_parallel": true, "self": 0.00039742799981468124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013604030000351486, "count": 8, "is_parallel": true, "self": 0.0013604030000351486 } } } } } } }, "UnityEnvironment.step": { "total": 1580.3671163300141, "count": 64041, "is_parallel": true, "self": 37.289857650943304, "children": { "UnityEnvironment._generate_step_input": { "total": 26.109477233012512, "count": 64041, "is_parallel": true, "self": 26.109477233012512 }, "communicator.exchange": { "total": 1405.0978563908848, "count": 64041, "is_parallel": true, "self": 1405.0978563908848 }, "steps_from_proto": { "total": 111.86992505517355, "count": 64041, "is_parallel": true, "self": 23.763585650517598, "children": { "_process_rank_one_or_two_observation": { "total": 88.10633940465596, "count": 512328, "is_parallel": true, "self": 88.10633940465596 } } } } } } } } } } }, "trainer_advance": { "total": 679.0674686439816, "count": 64042, "self": 3.124775060972752, "children": { "process_trajectory": { "total": 142.05708789099845, "count": 64042, "self": 141.79059333999976, "children": { "RLTrainer._checkpoint": { "total": 0.26649455099868646, "count": 2, "self": 0.26649455099868646 } } }, "_update_policy": { "total": 533.8856056920104, "count": 449, "self": 318.87912679486453, "children": { "TorchPPOOptimizer.update": { "total": 215.00647889714583, "count": 22794, "self": 215.00647889714583 } } } } } } }, "trainer_threads": { "total": 1.1350002750987187e-06, "count": 1, "self": 1.1350002750987187e-06 }, "TrainerController._save_models": { "total": 0.09696416499991756, "count": 1, "self": 0.0014571749998140149, "children": { "RLTrainer._checkpoint": { "total": 0.09550699000010354, "count": 1, "self": 0.09550699000010354 } } } } } } }