{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6090071201324463, "min": 0.6090071201324463, "max": 0.7083700299263, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 18416.375, "min": 7111.50048828125, "max": 21252.91796875, "count": 10 }, "Pyramids.Step.mean": { "value": 479911.0, "min": 209880.0, "max": 479911.0, "count": 10 }, "Pyramids.Step.sum": { "value": 479911.0, "min": 209880.0, "max": 479911.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07253942638635635, "min": -0.08320462703704834, "max": 0.0023477766662836075, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.48200225830078, "min": -20.05231475830078, "max": 0.5752052664756775, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022784555330872536, "min": 0.022784555330872536, "max": 0.06529036909341812, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.491077899932861, "min": 4.192404270172119, "max": 15.734979629516602, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06981263172146551, "min": 0.06703904121303025, "max": 0.07397912945776448, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9773768441005172, "min": 0.1435443493925656, "max": 1.0357078124087027, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0021188440727008596, "min": 0.0013612011227704492, "max": 0.0048058832548568825, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.02966381701781203, "min": 0.0027523123214905354, "max": 0.06728236556799636, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.109013582712857e-05, "min": 2.109013582712857e-05, "max": 0.0001762992412336, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00029526190157979997, "min": 0.00029526190157979997, "max": 0.0019769963410013994, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1070300142857143, "min": 0.1070300142857143, "max": 0.1587664, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4984202000000002, "min": 0.3175328, "max": 2.0026257999999997, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007122984271428573, "min": 0.0007122984271428573, "max": 0.005880763360000001, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.009972177980000002, "min": 0.009972177980000002, "max": 0.06595396014, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02221989631652832, "min": 0.02221989631652832, "max": 0.04772371053695679, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3110785484313965, "min": 0.09544742107391357, "max": 0.5373121500015259, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 979.1875, "min": 869.6176470588235, "max": 981.9666666666667, "count": 9 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31334.0, "min": 25939.0, "max": 31777.0, "count": 9 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7297750487923622, "min": -0.8492333829402924, "max": -0.22300592941396377, "count": 9 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -23.35280156135559, "min": -25.5498016923666, "max": -7.582201600074768, "count": 9 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7297750487923622, "min": -0.8492333829402924, "max": -0.22300592941396377, "count": 9 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -23.35280156135559, "min": -25.5498016923666, "max": -7.582201600074768, "count": 9 }, "Pyramids.Policy.RndReward.mean": { "value": 0.22445262252585962, "min": 0.22445262252585962, "max": 0.45849867131222377, "count": 9 }, "Pyramids.Policy.RndReward.sum": { "value": 7.182483920827508, "min": 6.778018158860505, "max": 15.130456153303385, "count": 9 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744797048", "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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744797673" }, "total": 624.632570834, "count": 1, "self": 0.4775936529995306, "children": { "run_training.setup": { "total": 0.020155083000190643, "count": 1, "self": 0.020155083000190643 }, "TrainerController.start_learning": { "total": 624.1348220980003, "count": 1, "self": 0.33929680506071236, "children": { "TrainerController._reset_env": { "total": 2.2091631130001588, "count": 1, "self": 2.2091631130001588 }, "TrainerController.advance": { "total": 621.5018639819405, "count": 19001, "self": 0.3557345230719875, "children": { "env_step": { "total": 425.8311929509264, "count": 19001, "self": 383.74839915102893, "children": { "SubprocessEnvManager._take_step": { "total": 41.88057261093854, "count": 19001, "self": 1.3218104008888076, "children": { "TorchPolicy.evaluate": { "total": 40.558762210049736, "count": 18822, "self": 40.558762210049736 } } }, "workers": { "total": 0.20222118895890162, "count": 19001, "self": 0.0, "children": { "worker_root": { "total": 622.6694001459628, "count": 19001, "is_parallel": true, "self": 269.59287153189416, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002057608000086475, "count": 1, "is_parallel": true, "self": 0.0006166229991322325, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014409850009542424, "count": 8, "is_parallel": true, "self": 0.0014409850009542424 } } }, "UnityEnvironment.step": { "total": 0.04956128100002388, "count": 1, "is_parallel": true, "self": 0.0005393860001277062, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004479619997255213, "count": 1, "is_parallel": true, "self": 0.0004479619997255213 }, "communicator.exchange": { "total": 0.04698090600004434, "count": 1, "is_parallel": true, "self": 0.04698090600004434 }, "steps_from_proto": { "total": 0.0015930270001263125, "count": 1, "is_parallel": true, "self": 0.0003434210002524196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012496059998738929, "count": 8, "is_parallel": true, "self": 0.0012496059998738929 } } } } } } }, "UnityEnvironment.step": { "total": 353.0765286140686, "count": 19000, "is_parallel": true, "self": 9.142413075109289, "children": { "UnityEnvironment._generate_step_input": { "total": 6.861393524020514, "count": 19000, "is_parallel": true, "self": 6.861393524020514 }, "communicator.exchange": { "total": 310.0955846810225, "count": 19000, "is_parallel": true, "self": 310.0955846810225 }, "steps_from_proto": { "total": 26.97713733391629, "count": 19000, "is_parallel": true, "self": 5.200288040794476, "children": { "_process_rank_one_or_two_observation": { "total": 21.776849293121813, "count": 152000, "is_parallel": true, "self": 21.776849293121813 } } } } } } } } } } }, "trainer_advance": { "total": 195.3149365079421, "count": 19001, "self": 0.6684364159968936, "children": { "process_trajectory": { "total": 35.69862378093694, "count": 19001, "self": 35.58427482393654, "children": { "RLTrainer._checkpoint": { "total": 0.11434895700040215, "count": 1, "self": 0.11434895700040215 } } }, "_update_policy": { "total": 158.94787631100826, "count": 132, "self": 88.18893193500344, "children": { "TorchPPOOptimizer.update": { "total": 70.75894437600482, "count": 6798, "self": 70.75894437600482 } } } } } } }, "trainer_threads": { "total": 9.159994078800082e-07, "count": 1, "self": 9.159994078800082e-07 }, "TrainerController._save_models": { "total": 0.08449728199957462, "count": 1, "self": 0.001875213999483094, "children": { "RLTrainer._checkpoint": { "total": 0.08262206800009153, "count": 1, "self": 0.08262206800009153 } } } } } } }