{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16678720712661743, "min": 0.15666288137435913, "max": 1.4213401079177856, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5078.3369140625, "min": 4707.40625, "max": 43117.7734375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999899.0, "min": 29913.0, "max": 2999899.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999899.0, "min": 29913.0, "max": 2999899.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.726608395576477, "min": -0.09833689033985138, "max": 0.8048906922340393, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 210.7164306640625, "min": -23.679702758789062, "max": 241.4672088623047, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008819431997835636, "min": -0.017887162044644356, "max": 0.41798147559165955, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5576353073120117, "min": -4.793759346008301, "max": 99.06160736083984, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0651302291745586, "min": 0.061494153037138996, "max": 0.07590447975310702, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9118232084438205, "min": 0.48960362881021946, "max": 1.0789062830815823, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01928012238169599, "min": 0.0002519643632288418, "max": 0.01928012238169599, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2699217133437439, "min": 0.0035275010852037847, "max": 0.2699217133437439, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4612709415142837e-06, "min": 1.4612709415142837e-06, "max": 0.00029841152910091906, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.045779318119997e-05, "min": 2.045779318119997e-05, "max": 0.003801197632934167, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048705714285718, "min": 0.10048705714285718, "max": 0.19947050952380954, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068188000000004, "min": 1.3962935666666667, "max": 2.667065833333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.865700857142851e-05, "min": 5.865700857142851e-05, "max": 0.00994710390142857, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008211981199999992, "min": 0.0008211981199999992, "max": 0.12671987675000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00768723851069808, "min": 0.007365300785750151, "max": 0.6202684640884399, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10762134194374084, "min": 0.10331115871667862, "max": 4.341879367828369, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 232.6220472440945, "min": 232.6220472440945, "max": 998.0625, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29543.0, "min": 16584.0, "max": 33998.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7358708510131349, "min": -0.9364688005298376, "max": 1.7359359136899002, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 220.45559807866812, "min": -30.56060167402029, "max": 222.19979695230722, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7358708510131349, "min": -0.9364688005298376, "max": 1.7359359136899002, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 220.45559807866812, "min": -30.56060167402029, "max": 222.19979695230722, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018593377168574482, "min": 0.018593377168574482, "max": 12.322986813152538, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.361358900408959, "min": 2.1953094323689584, "max": 209.49077582359314, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1777145876", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1777153999" }, "total": 8122.823681454, "count": 1, "self": 0.5973480659995403, "children": { "run_training.setup": { "total": 0.024158827999826826, "count": 1, "self": 0.024158827999826826 }, "TrainerController.start_learning": { "total": 8122.2021745600005, "count": 1, "self": 5.157569504035564, "children": { "TrainerController._reset_env": { "total": 2.6102732239999114, "count": 1, "self": 2.6102732239999114 }, "TrainerController.advance": { "total": 8114.348141091966, "count": 193907, "self": 5.308057010827724, "children": { "env_step": { "total": 5929.773578725045, "count": 193907, "self": 5388.145519717626, "children": { "SubprocessEnvManager._take_step": { "total": 538.5754757252159, "count": 193907, "self": 15.742440588412364, "children": { "TorchPolicy.evaluate": { "total": 522.8330351368036, "count": 187563, "self": 522.8330351368036 } } }, "workers": { "total": 3.0525832822036136, "count": 193907, "self": 0.0, "children": { "worker_root": { "total": 8101.863911016021, "count": 193907, "is_parallel": true, "self": 3139.6670245233536, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019383829999242153, "count": 1, "is_parallel": true, "self": 0.0006330079997951543, "children": { "_process_rank_one_or_two_observation": { "total": 0.001305375000129061, "count": 8, "is_parallel": true, "self": 0.001305375000129061 } } }, "UnityEnvironment.step": { "total": 0.08771635800007971, "count": 1, "is_parallel": true, "self": 0.0005497220001871028, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005800390001695632, "count": 1, "is_parallel": true, "self": 0.0005800390001695632 }, "communicator.exchange": { "total": 0.08091637299980903, "count": 1, "is_parallel": true, "self": 0.08091637299980903 }, "steps_from_proto": { "total": 0.005670223999914015, "count": 1, "is_parallel": true, "self": 0.0003767440000501665, "children": { "_process_rank_one_or_two_observation": { "total": 0.005293479999863848, "count": 8, "is_parallel": true, "self": 0.005293479999863848 } } } } } } }, "UnityEnvironment.step": { "total": 4962.1968864926675, "count": 193906, "is_parallel": true, "self": 120.2270590923672, "children": { "UnityEnvironment._generate_step_input": { "total": 82.0071565852079, "count": 193906, "is_parallel": true, "self": 82.0071565852079 }, "communicator.exchange": { "total": 4378.982553259242, "count": 193906, "is_parallel": true, "self": 4378.982553259242 }, "steps_from_proto": { "total": 380.98011755585094, "count": 193906, "is_parallel": true, "self": 79.14571468502095, "children": { "_process_rank_one_or_two_observation": { "total": 301.83440287083, "count": 1551248, "is_parallel": true, "self": 301.83440287083 } } } } } } } } } } }, "trainer_advance": { "total": 2179.266505356093, "count": 193907, "self": 10.051591829389508, "children": { "process_trajectory": { "total": 426.6326890487096, "count": 193907, "self": 426.0325012007104, "children": { "RLTrainer._checkpoint": { "total": 0.6001878479992229, "count": 6, "self": 0.6001878479992229 } } }, "_update_policy": { "total": 1742.582224477994, "count": 1391, "self": 952.8126153092271, "children": { "TorchPPOOptimizer.update": { "total": 789.7696091687669, "count": 68340, "self": 789.7696091687669 } } } } } } }, "trainer_threads": { "total": 2.0139996195212007e-06, "count": 1, "self": 2.0139996195212007e-06 }, "TrainerController._save_models": { "total": 0.08618872599981842, "count": 1, "self": 0.0010075120007968508, "children": { "RLTrainer._checkpoint": { "total": 0.08518121399902157, "count": 1, "self": 0.08518121399902157 } } } } } } }