{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.211785227060318, "min": 0.1946796178817749, "max": 1.5224860906600952, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6326.4482421875, "min": 5834.15869140625, "max": 46186.13671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7602939009666443, "min": -0.07265773415565491, "max": 0.7602939009666443, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 222.0058135986328, "min": -17.510513305664062, "max": 222.0058135986328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.040066372603178024, "min": 0.040066372603178024, "max": 1.1749746799468994, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.699380874633789, "min": 11.699380874633789, "max": 283.16888427734375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.03294433915011939, "min": 0.028475876946079857, "max": 0.04587337804189178, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.23061037405083576, "min": 0.18349351216756712, "max": 0.27638394188640325, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015712156816984395, "min": 0.0038830644961091736, "max": 0.02327030710993579, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10998509771889077, "min": 0.027181451472764215, "max": 0.12701877288054675, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.912040219828571e-06, "min": 7.912040219828571e-06, "max": 0.00029544960151680006, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.53842815388e-05, "min": 5.53842815388e-05, "max": 0.0019394424535191998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10263731428571429, "min": 0.10263731428571429, "max": 0.19848320000000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7184612, "min": 0.7184612, "max": 1.3960433, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00027346769714285717, "min": 0.00027346769714285717, "max": 0.009848471680000002, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0019142738800000004, "min": 0.0019142738800000004, "max": 0.06465343192, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03420932963490486, "min": 0.03420932963490486, "max": 1.5784579515457153, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23946531116962433, "min": 0.23946531116962433, "max": 6.313831806182861, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 249.64705882352942, "min": 249.64705882352942, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29708.0, "min": 15984.0, "max": 33271.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7503529301210612, "min": -1.0000000521540642, "max": 1.7503529301210612, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 208.29199868440628, "min": -29.245001673698425, "max": 209.1213981807232, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7503529301210612, "min": -1.0000000521540642, "max": 1.7503529301210612, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 208.29199868440628, "min": -29.245001673698425, "max": 209.1213981807232, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08683016150529466, "min": 0.08683016150529466, "max": 19.198913529515266, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 10.332789219130063, "min": 10.332789219130063, "max": 510.13557055592537, "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": "1741228206", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1741232345" }, "total": 4138.321809829, "count": 1, "self": 0.47562991899940243, "children": { "run_training.setup": { "total": 0.10751997299996674, "count": 1, "self": 0.10751997299996674 }, "TrainerController.start_learning": { "total": 4137.738659937, "count": 1, "self": 2.1328908790274, "children": { "TrainerController._reset_env": { "total": 6.418224683999995, "count": 1, "self": 6.418224683999995 }, "TrainerController.advance": { "total": 4128.719837755973, "count": 64835, "self": 2.1788465019526484, "children": { "env_step": { "total": 2254.438757555011, "count": 64835, "self": 1923.9197663909936, "children": { "SubprocessEnvManager._take_step": { "total": 329.24431494997634, "count": 64835, "self": 7.465833500981489, "children": { "TorchPolicy.evaluate": { "total": 321.77848144899485, "count": 62559, "self": 321.77848144899485 } } }, "workers": { "total": 1.2746762140409373, "count": 64835, "self": 0.0, "children": { "worker_root": { "total": 4133.126782388971, "count": 64835, "is_parallel": true, "self": 2371.8190018989253, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00279798200000414, "count": 1, "is_parallel": true, "self": 0.0009069270000736651, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018910549999304749, "count": 8, "is_parallel": true, "self": 0.0018910549999304749 } } }, "UnityEnvironment.step": { "total": 0.049881557999981396, "count": 1, "is_parallel": true, "self": 0.0007859379999786142, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006339110000226356, "count": 1, "is_parallel": true, "self": 0.0006339110000226356 }, "communicator.exchange": { "total": 0.04627840199998445, "count": 1, "is_parallel": true, "self": 0.04627840199998445 }, "steps_from_proto": { "total": 0.0021833069999956933, "count": 1, "is_parallel": true, "self": 0.00047210000002451125, "children": { "_process_rank_one_or_two_observation": { "total": 0.001711206999971182, "count": 8, "is_parallel": true, "self": 0.001711206999971182 } } } } } } }, "UnityEnvironment.step": { "total": 1761.307780490046, "count": 64834, "is_parallel": true, "self": 41.71716790626556, "children": { "UnityEnvironment._generate_step_input": { "total": 28.109792606913743, "count": 64834, "is_parallel": true, "self": 28.109792606913743 }, "communicator.exchange": { "total": 1588.2742161969807, "count": 64834, "is_parallel": true, "self": 1588.2742161969807 }, "steps_from_proto": { "total": 103.20660377988622, "count": 64834, "is_parallel": true, "self": 22.666827304719106, "children": { "_process_rank_one_or_two_observation": { "total": 80.53977647516712, "count": 518672, "is_parallel": true, "self": 80.53977647516712 } } } } } } } } } } }, "trainer_advance": { "total": 1872.1022336990093, "count": 64835, "self": 4.3382759709991205, "children": { "process_trajectory": { "total": 266.6639659390084, "count": 64835, "self": 265.79424973100816, "children": { "RLTrainer._checkpoint": { "total": 0.8697162080002272, "count": 2, "self": 0.8697162080002272 } } }, "_update_policy": { "total": 1601.0999917890017, "count": 235, "self": 271.64368517001026, "children": { "TorchPPOOptimizer.update": { "total": 1329.4563066189914, "count": 5754, "self": 1329.4563066189914 } } } } } } }, "trainer_threads": { "total": 2.124000275216531e-06, "count": 1, "self": 2.124000275216531e-06 }, "TrainerController._save_models": { "total": 0.46770449399991776, "count": 1, "self": 0.016055266999501328, "children": { "RLTrainer._checkpoint": { "total": 0.45164922700041643, "count": 1, "self": 0.45164922700041643 } } } } } } }