{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33612048625946045, "min": 0.3304068446159363, "max": 1.513931393623352, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10067.48046875, "min": 9961.478515625, "max": 45926.62109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.28742852807044983, "min": -0.1232360303401947, "max": 0.30877771973609924, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 74.44398498535156, "min": -29.206939697265625, "max": 80.89976501464844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.022946611046791077, "min": -0.052843138575553894, "max": 0.3748281002044678, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.943172454833984, "min": -13.897745132446289, "max": 88.83425903320312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06577681457791995, "min": 0.06336787613626156, "max": 0.07478650453216006, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9866522186687993, "min": 0.49247738016078824, "max": 1.010375064961036, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012354451758761164, "min": 0.00011568347980343896, "max": 0.013553259147722267, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18531677638141747, "min": 0.001480024090557454, "max": 0.18974562806811174, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.510877496406664e-06, "min": 7.510877496406664e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011266316244609996, "min": 0.00011266316244609996, "max": 0.0033758395747202, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250359333333334, "min": 0.10250359333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375539, "min": 1.3691136000000002, "max": 2.4252798, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002601089739999999, "min": 0.0002601089739999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039016346099999986, "min": 0.0039016346099999986, "max": 0.11254545202, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008992094546556473, "min": 0.008992094546556473, "max": 0.3358005881309509, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1348814219236374, "min": 0.13072361052036285, "max": 2.3506040573120117, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 523.4237288135594, "min": 491.4918032786885, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30882.0, "min": 15984.0, "max": 32560.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.137491497447935, "min": -1.0000000521540642, "max": 1.1878096491338745, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.11199834942818, "min": -32.000001668930054, "max": 73.64419824630022, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.137491497447935, "min": -1.0000000521540642, "max": 1.1878096491338745, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.11199834942818, "min": -32.000001668930054, "max": 73.64419824630022, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04971082545461733, "min": 0.04704906155682458, "max": 7.081634526606649, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9329387018224224, "min": 2.917041816523124, "max": 113.30615242570639, "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": "1788899945", "python_version": "3.10.12 (main, Jun 22 2026, 18:55:27) [GCC 11.4.0]", "command_line_arguments": "/home/duc10u/.cache/uv/builds-v0/.tmpRLNXyV/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1788902006" }, "total": 2059.7892925219985, "count": 1, "self": 0.6766355709969503, "children": { "run_training.setup": { "total": 0.02570900899991102, "count": 1, "self": 0.02570900899991102 }, "TrainerController.start_learning": { "total": 2059.0869479420016, "count": 1, "self": 1.3129788389233, "children": { "TrainerController._reset_env": { "total": 2.701139762000821, "count": 1, "self": 2.701139762000821 }, "TrainerController.advance": { "total": 2054.9909305910787, "count": 63335, "self": 1.1634479202093644, "children": { "env_step": { "total": 1488.9216896508442, "count": 63335, "self": 1310.1777050786368, "children": { "SubprocessEnvManager._take_step": { "total": 177.84450034622023, "count": 63335, "self": 4.098916838482182, "children": { "TorchPolicy.evaluate": { "total": 173.74558350773805, "count": 62574, "self": 173.74558350773805 } } }, "workers": { "total": 0.8994842259871803, "count": 63335, "self": 0.0, "children": { "worker_root": { "total": 2055.3203698071648, "count": 63335, "is_parallel": true, "self": 832.80435911727, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002109440998538048, "count": 1, "is_parallel": true, "self": 0.0007262789986270946, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013831619999109535, "count": 8, "is_parallel": true, "self": 0.0013831619999109535 } } }, "UnityEnvironment.step": { "total": 0.037860046000787406, "count": 1, "is_parallel": true, "self": 0.0001871980039140908, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022944199918129016, "count": 1, "is_parallel": true, "self": 0.00022944199918129016 }, "communicator.exchange": { "total": 0.03679235599884123, "count": 1, "is_parallel": true, "self": 0.03679235599884123 }, "steps_from_proto": { "total": 0.0006510499988507945, "count": 1, "is_parallel": true, "self": 0.00013183999726606999, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005192100015847245, "count": 8, "is_parallel": true, "self": 0.0005192100015847245 } } } } } } }, "UnityEnvironment.step": { "total": 1222.5160106898948, "count": 63334, "is_parallel": true, "self": 14.855550148960901, "children": { "UnityEnvironment._generate_step_input": { "total": 11.636540973837327, "count": 63334, "is_parallel": true, "self": 11.636540973837327 }, "communicator.exchange": { "total": 1154.4404662274155, "count": 63334, "is_parallel": true, "self": 1154.4404662274155 }, "steps_from_proto": { "total": 41.583453339681, "count": 63334, "is_parallel": true, "self": 9.493436596254469, "children": { "_process_rank_one_or_two_observation": { "total": 32.09001674342653, "count": 506672, "is_parallel": true, "self": 32.09001674342653 } } } } } } } } } } }, "trainer_advance": { "total": 564.9057930200252, "count": 63335, "self": 2.472755813087133, "children": { "process_trajectory": { "total": 88.78879767590479, "count": 63335, "self": 88.60193946390064, "children": { "RLTrainer._checkpoint": { "total": 0.18685821200415376, "count": 2, "self": 0.18685821200415376 } } }, "_update_policy": { "total": 473.64423953103324, "count": 436, "self": 212.50300034686552, "children": { "TorchPPOOptimizer.update": { "total": 261.1412391841677, "count": 22773, "self": 261.1412391841677 } } } } } } }, "trainer_threads": { "total": 7.300004654098302e-07, "count": 1, "self": 7.300004654098302e-07 }, "TrainerController._save_models": { "total": 0.08189801999833435, "count": 1, "self": 0.0014402279957721476, "children": { "RLTrainer._checkpoint": { "total": 0.0804577920025622, "count": 1, "self": 0.0804577920025622 } } } } } } }