{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47023603320121765, "min": 0.46864181756973267, "max": 1.4444211721420288, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14310.22265625, "min": 13976.7734375, "max": 43817.9609375, "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": 0.5939630270004272, "min": -0.09947913140058517, "max": 0.5939630270004272, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.6855010986328, "min": -23.87499237060547, "max": 168.6855010986328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.010013428516685963, "min": -0.06413896381855011, "max": 0.2337827980518341, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.84381365776062, "min": -17.638216018676758, "max": 56.107872009277344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0666810920464784, "min": 0.06353942904428479, "max": 0.07294189150870778, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9335352886506977, "min": 0.4672190510786952, "max": 1.0721203224772278, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013154421738276832, "min": 0.0004745043597792023, "max": 0.014844499736639028, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18416190433587565, "min": 0.005219547957571225, "max": 0.20992159002087327, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.6123617482928615e-06, "min": 7.6123617482928615e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010657306447610006, "min": 0.00010657306447610006, "max": 0.0032553458148847996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253742142857143, "min": 0.10253742142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355239, "min": 1.3691136000000002, "max": 2.4016112, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002634884007142859, "min": 0.0002634884007142859, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036888376100000023, "min": 0.0036888376100000023, "max": 0.10853300848, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009013361297547817, "min": 0.009013361297547817, "max": 0.34724658727645874, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1261870563030243, "min": 0.1261870563030243, "max": 2.4307260513305664, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 325.494623655914, "min": 325.494623655914, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30271.0, "min": 15984.0, "max": 32514.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5884494445016306, "min": -1.0000000521540642, "max": 1.5884494445016306, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.72579833865166, "min": -32.000001668930054, "max": 147.72579833865166, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5884494445016306, "min": -1.0000000521540642, "max": 1.5884494445016306, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.72579833865166, "min": -32.000001668930054, "max": 147.72579833865166, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030123901632939896, "min": 0.030123901632939896, "max": 7.160688947886229, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8015228518634103, "min": 2.7883641324588098, "max": 114.57102316617966, "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": "1711317227", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711319329" }, "total": 2101.330377086, "count": 1, "self": 0.4821634449999692, "children": { "run_training.setup": { "total": 0.05299005999995643, "count": 1, "self": 0.05299005999995643 }, "TrainerController.start_learning": { "total": 2100.7952235810003, "count": 1, "self": 1.4473202829985894, "children": { "TrainerController._reset_env": { "total": 2.0147021230000064, "count": 1, "self": 2.0147021230000064 }, "TrainerController.advance": { "total": 2097.2465140870017, "count": 63654, "self": 1.463257029169199, "children": { "env_step": { "total": 1471.333353609943, "count": 63654, "self": 1334.5134688929352, "children": { "SubprocessEnvManager._take_step": { "total": 135.9445595770917, "count": 63654, "self": 4.971099847175992, "children": { "TorchPolicy.evaluate": { "total": 130.9734597299157, "count": 62559, "self": 130.9734597299157 } } }, "workers": { "total": 0.8753251399161854, "count": 63654, "self": 0.0, "children": { "worker_root": { "total": 2095.4733482290094, "count": 63654, "is_parallel": true, "self": 885.5743458501211, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002060457999959908, "count": 1, "is_parallel": true, "self": 0.0005913659992984321, "children": { "_process_rank_one_or_two_observation": { "total": 0.001469092000661476, "count": 8, "is_parallel": true, "self": 0.001469092000661476 } } }, "UnityEnvironment.step": { "total": 0.04921046400022533, "count": 1, "is_parallel": true, "self": 0.0007085660004122474, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004699289997915912, "count": 1, "is_parallel": true, "self": 0.0004699289997915912 }, "communicator.exchange": { "total": 0.046240814000157116, "count": 1, "is_parallel": true, "self": 0.046240814000157116 }, "steps_from_proto": { "total": 0.001791154999864375, "count": 1, "is_parallel": true, "self": 0.0003755369998543756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014156180000099994, "count": 8, "is_parallel": true, "self": 0.0014156180000099994 } } } } } } }, "UnityEnvironment.step": { "total": 1209.8990023788883, "count": 63653, "is_parallel": true, "self": 34.79453368471195, "children": { "UnityEnvironment._generate_step_input": { "total": 24.37731456102074, "count": 63653, "is_parallel": true, "self": 24.37731456102074 }, "communicator.exchange": { "total": 1046.82011057102, "count": 63653, "is_parallel": true, "self": 1046.82011057102 }, "steps_from_proto": { "total": 103.90704356213564, "count": 63653, "is_parallel": true, "self": 21.24826870225388, "children": { "_process_rank_one_or_two_observation": { "total": 82.65877485988176, "count": 509224, "is_parallel": true, "self": 82.65877485988176 } } } } } } } } } } }, "trainer_advance": { "total": 624.4499034478895, "count": 63654, "self": 2.7783357469161274, "children": { "process_trajectory": { "total": 130.29755263797279, "count": 63654, "self": 130.09955614797263, "children": { "RLTrainer._checkpoint": { "total": 0.19799649000015052, "count": 2, "self": 0.19799649000015052 } } }, "_update_policy": { "total": 491.37401506300057, "count": 443, "self": 288.3850305619576, "children": { "TorchPPOOptimizer.update": { "total": 202.98898450104298, "count": 22809, "self": 202.98898450104298 } } } } } } }, "trainer_threads": { "total": 1.0169997040065937e-06, "count": 1, "self": 1.0169997040065937e-06 }, "TrainerController._save_models": { "total": 0.08668607100025838, "count": 1, "self": 0.0013398379996942822, "children": { "RLTrainer._checkpoint": { "total": 0.0853462330005641, "count": 1, "self": 0.0853462330005641 } } } } } } }