{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29171937704086304, "min": 0.2769649922847748, "max": 1.420454502105713, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8882.271484375, "min": 8242.478515625, "max": 43090.90625, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29990.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29990.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6061269640922546, "min": -0.0911201685667038, "max": 0.6337053179740906, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 170.9278106689453, "min": -21.9599609375, "max": 178.000244140625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.037593163549900055, "min": 0.031334586441516876, "max": 0.6855327486991882, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.601272583007812, "min": 8.679680824279785, "max": 163.15679931640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06897025133560722, "min": 0.06516827440225621, "max": 0.07382230501042655, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0345537700341083, "min": 0.5776085983114062, "max": 1.049290242485072, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014817604419335518, "min": 0.0010869009640006985, "max": 0.018632207809338636, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22226406629003276, "min": 0.013042811568008381, "max": 0.22226406629003276, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.523377492240001e-06, "min": 7.523377492240001e-06, "max": 0.000294850126716625, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011285066238360002, "min": 0.00011285066238360002, "max": 0.0036327082890972996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250776000000002, "min": 0.10250776000000002, "max": 0.19828337499999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376164000000003, "min": 1.4777268000000001, "max": 2.6172413000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002605252240000001, "min": 0.0002605252240000001, "max": 0.009828509162499999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003907878360000001, "min": 0.003907878360000001, "max": 0.12110917973000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.043476954102516174, "min": 0.043476954102516174, "max": 0.7161552906036377, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.6521543264389038, "min": 0.631241500377655, "max": 5.729242324829102, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 323.1530612244898, "min": 301.22, "max": 980.65625, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31669.0, "min": 16405.0, "max": 33804.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6156020216947915, "min": -0.9189875507727265, "max": 1.6834456348872704, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.32899812608957, "min": -29.40760162472725, "max": 167.87739872932434, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6156020216947915, "min": -0.9189875507727265, "max": 1.6834456348872704, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.32899812608957, "min": -29.40760162472725, "max": 167.87739872932434, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.14359090987673714, "min": 0.14057873103992788, "max": 15.49724436945775, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 14.07190916792024, "min": 12.792664524633437, "max": 263.45315428078175, "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": "1739104605", "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": "1739106904" }, "total": 2299.11655875, "count": 1, "self": 0.5255652640003063, "children": { "run_training.setup": { "total": 0.019757444999868312, "count": 1, "self": 0.019757444999868312 }, "TrainerController.start_learning": { "total": 2298.571236041, "count": 1, "self": 1.436835712080665, "children": { "TrainerController._reset_env": { "total": 2.2430026209999596, "count": 1, "self": 2.2430026209999596 }, "TrainerController.advance": { "total": 2294.8020783019183, "count": 64184, "self": 1.409844629721647, "children": { "env_step": { "total": 1601.811925155006, "count": 64184, "self": 1445.5094902478863, "children": { "SubprocessEnvManager._take_step": { "total": 155.4796501159517, "count": 64184, "self": 4.74123251905894, "children": { "TorchPolicy.evaluate": { "total": 150.73841759689276, "count": 62562, "self": 150.73841759689276 } } }, "workers": { "total": 0.8227847911680328, "count": 64184, "self": 0.0, "children": { "worker_root": { "total": 2293.3001151820745, "count": 64184, "is_parallel": true, "self": 962.3882109671745, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019683470000018133, "count": 1, "is_parallel": true, "self": 0.0006198410010256339, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013485059989761794, "count": 8, "is_parallel": true, "self": 0.0013485059989761794 } } }, "UnityEnvironment.step": { "total": 0.048794057999657525, "count": 1, "is_parallel": true, "self": 0.0005461470000227564, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004652729999179428, "count": 1, "is_parallel": true, "self": 0.0004652729999179428 }, "communicator.exchange": { "total": 0.04621448599982614, "count": 1, "is_parallel": true, "self": 0.04621448599982614 }, "steps_from_proto": { "total": 0.0015681519998906879, "count": 1, "is_parallel": true, "self": 0.0003322409993415931, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012359110005490948, "count": 8, "is_parallel": true, "self": 0.0012359110005490948 } } } } } } }, "UnityEnvironment.step": { "total": 1330.9119042149, "count": 64183, "is_parallel": true, "self": 31.455955283623553, "children": { "UnityEnvironment._generate_step_input": { "total": 22.346871572081, "count": 64183, "is_parallel": true, "self": 22.346871572081 }, "communicator.exchange": { "total": 1183.8362946160983, "count": 64183, "is_parallel": true, "self": 1183.8362946160983 }, "steps_from_proto": { "total": 93.2727827430972, "count": 64183, "is_parallel": true, "self": 18.63844032111183, "children": { "_process_rank_one_or_two_observation": { "total": 74.63434242198537, "count": 513464, "is_parallel": true, "self": 74.63434242198537 } } } } } } } } } } }, "trainer_advance": { "total": 691.5803085171906, "count": 64184, "self": 2.8012643603328797, "children": { "process_trajectory": { "total": 130.24461101385214, "count": 64184, "self": 130.03532119285182, "children": { "RLTrainer._checkpoint": { "total": 0.20928982100031135, "count": 2, "self": 0.20928982100031135 } } }, "_update_policy": { "total": 558.5344331430056, "count": 458, "self": 309.11288980796917, "children": { "TorchPPOOptimizer.update": { "total": 249.4215433350364, "count": 22785, "self": 249.4215433350364 } } } } } } }, "trainer_threads": { "total": 8.570004865759984e-07, "count": 1, "self": 8.570004865759984e-07 }, "TrainerController._save_models": { "total": 0.08931854900038161, "count": 1, "self": 0.0014576290004697512, "children": { "RLTrainer._checkpoint": { "total": 0.08786091999991186, "count": 1, "self": 0.08786091999991186 } } } } } } }