{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2717469036579132, "min": 0.27156588435173035, "max": 1.4876023530960083, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8108.927734375, "min": 8108.927734375, "max": 45127.90625, "count": 33 }, "Pyramids.Step.mean": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6511969566345215, "min": -0.25794675946235657, "max": 0.6511969566345215, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 183.63754272460938, "min": -61.133384704589844, "max": 184.67904663085938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026966197416186333, "min": 0.00104394624941051, "max": 0.19469797611236572, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.604467868804932, "min": 0.29752469062805176, "max": 46.922210693359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06940526702365948, "min": 0.06613975985757341, "max": 0.07636661407549131, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9716737383312327, "min": 0.5345662985284392, "max": 1.0471984722535126, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013673427092155679, "min": 0.001640879520910597, "max": 0.015217248001573393, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19142797929017952, "min": 0.016004557919950407, "max": 0.2282587200236009, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.327104700521433e-06, "min": 7.327104700521433e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010257946580730006, "min": 0.00010257946580730006, "max": 0.003383421872192799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244233571428571, "min": 0.10244233571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341926999999999, "min": 1.3886848, "max": 2.5278072000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000253989337857143, "min": 0.000253989337857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035558507300000024, "min": 0.0035558507300000024, "max": 0.11280793928, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01364502776414156, "min": 0.01364502776414156, "max": 0.3727685511112213, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1910303831100464, "min": 0.1910303831100464, "max": 2.609379768371582, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.17171717171715, "min": 299.17171717171715, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29618.0, "min": 15984.0, "max": 34424.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6402080667139305, "min": -1.0000000521540642, "max": 1.6713249889823298, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.3805986046791, "min": -30.565801717340946, "max": 162.3805986046791, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6402080667139305, "min": -1.0000000521540642, "max": 1.6713249889823298, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.3805986046791, "min": -30.565801717340946, "max": 162.3805986046791, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04276967525580366, "min": 0.04276967525580366, "max": 6.8422236777842045, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.234197850324563, "min": 4.234197850324563, "max": 109.47557884454727, "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": "1740345409", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740348011" }, "total": 2601.613257203, "count": 1, "self": 0.490582379999978, "children": { "run_training.setup": { "total": 0.0339401319999979, "count": 1, "self": 0.0339401319999979 }, "TrainerController.start_learning": { "total": 2601.0887346910004, "count": 1, "self": 1.7714010510053413, "children": { "TrainerController._reset_env": { "total": 3.2981948189999457, "count": 1, "self": 3.2981948189999457 }, "TrainerController.advance": { "total": 2595.9157456569956, "count": 64012, "self": 1.7413770560347075, "children": { "env_step": { "total": 1852.3437026379866, "count": 64012, "self": 1665.610401021966, "children": { "SubprocessEnvManager._take_step": { "total": 185.70540941399133, "count": 64012, "self": 5.59757602201114, "children": { "TorchPolicy.evaluate": { "total": 180.1078333919802, "count": 62559, "self": 180.1078333919802 } } }, "workers": { "total": 1.0278922020293066, "count": 64012, "self": 0.0, "children": { "worker_root": { "total": 2594.857883069073, "count": 64012, "is_parallel": true, "self": 1066.054954416049, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0064289030000281855, "count": 1, "is_parallel": true, "self": 0.004261131000021123, "children": { "_process_rank_one_or_two_observation": { "total": 0.002167772000007062, "count": 8, "is_parallel": true, "self": 0.002167772000007062 } } }, "UnityEnvironment.step": { "total": 0.05341775299996243, "count": 1, "is_parallel": true, "self": 0.0005608279999478327, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047599600009107235, "count": 1, "is_parallel": true, "self": 0.00047599600009107235 }, "communicator.exchange": { "total": 0.05038066199995228, "count": 1, "is_parallel": true, "self": 0.05038066199995228 }, "steps_from_proto": { "total": 0.0020002669999712452, "count": 1, "is_parallel": true, "self": 0.000561204999939946, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014390620000312992, "count": 8, "is_parallel": true, "self": 0.0014390620000312992 } } } } } } }, "UnityEnvironment.step": { "total": 1528.802928653024, "count": 64011, "is_parallel": true, "self": 36.97193641593594, "children": { "UnityEnvironment._generate_step_input": { "total": 27.272410580029828, "count": 64011, "is_parallel": true, "self": 27.272410580029828 }, "communicator.exchange": { "total": 1352.1338762429555, "count": 64011, "is_parallel": true, "self": 1352.1338762429555 }, "steps_from_proto": { "total": 112.42470541410285, "count": 64011, "is_parallel": true, "self": 23.670980141022596, "children": { "_process_rank_one_or_two_observation": { "total": 88.75372527308025, "count": 512088, "is_parallel": true, "self": 88.75372527308025 } } } } } } } } } } }, "trainer_advance": { "total": 741.8306659629742, "count": 64012, "self": 3.294330944989497, "children": { "process_trajectory": { "total": 143.54548593698905, "count": 64012, "self": 143.28468179798892, "children": { "RLTrainer._checkpoint": { "total": 0.260804139000129, "count": 2, "self": 0.260804139000129 } } }, "_update_policy": { "total": 594.9908490809956, "count": 452, "self": 326.65521285198815, "children": { "TorchPPOOptimizer.update": { "total": 268.3356362290075, "count": 22806, "self": 268.3356362290075 } } } } } } }, "trainer_threads": { "total": 1.0099997780343983e-06, "count": 1, "self": 1.0099997780343983e-06 }, "TrainerController._save_models": { "total": 0.1033921539997209, "count": 1, "self": 0.0014339439999275783, "children": { "RLTrainer._checkpoint": { "total": 0.10195820999979333, "count": 1, "self": 0.10195820999979333 } } } } } } }