{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35669174790382385, "min": 0.35669174790382385, "max": 1.49954092502594, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10786.3583984375, "min": 10786.3583984375, "max": 45490.07421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7356852889060974, "min": -0.08315018564462662, "max": 0.7356852889060974, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 211.8773651123047, "min": -20.039194107055664, "max": 211.8773651123047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01350936759263277, "min": -0.0029415858443826437, "max": 0.10930324345827103, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.890697956085205, "min": -0.72068852186203, "max": 25.904869079589844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06938899178794065, "min": 0.06752558936111329, "max": 0.07408185305394, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9714458850311691, "min": 0.51857297137758, "max": 1.098400202057639, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012605636305725514, "min": 0.00043579552627362906, "max": 0.014423261025222017, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1764789082801572, "min": 0.005665341841557178, "max": 0.21634891537833026, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.598111753042854e-06, "min": 7.598111753042854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010637356454259996, "min": 0.00010637356454259996, "max": 0.0037568902477032994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253267142857145, "min": 0.10253267142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354574000000002, "min": 1.3886848, "max": 2.6622153000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002630138757142857, "min": 0.0002630138757142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036821942599999996, "min": 0.0036821942599999996, "max": 0.12524444032999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004645850509405136, "min": 0.004645850509405136, "max": 0.1667596995830536, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0650419071316719, "min": 0.0650419071316719, "max": 1.1673178672790527, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 284.97222222222223, "min": 278.63392857142856, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30777.0, "min": 15984.0, "max": 32808.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.71502776099024, "min": -1.0000000521540642, "max": 1.71502776099024, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.22299818694592, "min": -28.431001745164394, "max": 186.66999752819538, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.71502776099024, "min": -1.0000000521540642, "max": 1.71502776099024, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.22299818694592, "min": -28.431001745164394, "max": 186.66999752819538, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015368654169799777, "min": 0.014709912489504658, "max": 5.284002441447228, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.659814650338376, "min": 1.5704724689567229, "max": 84.54403906315565, "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": "1746532210", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746535548" }, "total": 3338.133698483, "count": 1, "self": 0.5756392199996299, "children": { "run_training.setup": { "total": 0.020516402999874117, "count": 1, "self": 0.020516402999874117 }, "TrainerController.start_learning": { "total": 3337.5375428600005, "count": 1, "self": 1.2783874111019031, "children": { "TrainerController._reset_env": { "total": 2.3307660539999233, "count": 1, "self": 2.3307660539999233 }, "TrainerController.advance": { "total": 3333.8729060758988, "count": 64299, "self": 1.3388992697741742, "children": { "env_step": { "total": 1471.8256366041533, "count": 64299, "self": 1332.849743312131, "children": { "SubprocessEnvManager._take_step": { "total": 138.27599608801665, "count": 64299, "self": 4.400631626231188, "children": { "TorchPolicy.evaluate": { "total": 133.87536446178547, "count": 62557, "self": 133.87536446178547 } } }, "workers": { "total": 0.6998972040055378, "count": 64299, "self": 0.0, "children": { "worker_root": { "total": 3333.392712010082, "count": 64299, "is_parallel": true, "self": 2106.307662831081, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002042380000148114, "count": 1, "is_parallel": true, "self": 0.0006888170000820537, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013535630000660603, "count": 8, "is_parallel": true, "self": 0.0013535630000660603 } } }, "UnityEnvironment.step": { "total": 0.058164294000107475, "count": 1, "is_parallel": true, "self": 0.0005190980000406853, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044141399985164753, "count": 1, "is_parallel": true, "self": 0.00044141399985164753 }, "communicator.exchange": { "total": 0.055762344999948255, "count": 1, "is_parallel": true, "self": 0.055762344999948255 }, "steps_from_proto": { "total": 0.0014414370002668875, "count": 1, "is_parallel": true, "self": 0.0002864750008484407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011549619994184468, "count": 8, "is_parallel": true, "self": 0.0011549619994184468 } } } } } } }, "UnityEnvironment.step": { "total": 1227.085049179001, "count": 64298, "is_parallel": true, "self": 30.49961575105135, "children": { "UnityEnvironment._generate_step_input": { "total": 22.518682924971927, "count": 64298, "is_parallel": true, "self": 22.518682924971927 }, "communicator.exchange": { "total": 1083.3413522300116, "count": 64298, "is_parallel": true, "self": 1083.3413522300116 }, "steps_from_proto": { "total": 90.72539827296623, "count": 64298, "is_parallel": true, "self": 17.728588777489676, "children": { "_process_rank_one_or_two_observation": { "total": 72.99680949547655, "count": 514384, "is_parallel": true, "self": 72.99680949547655 } } } } } } } } } } }, "trainer_advance": { "total": 1860.7083702019713, "count": 64299, "self": 2.4377032029792645, "children": { "process_trajectory": { "total": 125.15031022298399, "count": 64299, "self": 125.00034010998434, "children": { "RLTrainer._checkpoint": { "total": 0.1499701129996538, "count": 2, "self": 0.1499701129996538 } } }, "_update_policy": { "total": 1733.120356776008, "count": 459, "self": 958.7386859411481, "children": { "TorchPPOOptimizer.update": { "total": 774.38167083486, "count": 76020, "self": 774.38167083486 } } } } } } }, "trainer_threads": { "total": 8.469996828353032e-07, "count": 1, "self": 8.469996828353032e-07 }, "TrainerController._save_models": { "total": 0.055482472000221605, "count": 1, "self": 0.0006966979999560863, "children": { "RLTrainer._checkpoint": { "total": 0.05478577400026552, "count": 1, "self": 0.05478577400026552 } } } } } } }