{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5476966500282288, "min": 0.5476966500282288, "max": 1.4472193717956543, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16325.7421875, "min": 16325.7421875, "max": 43902.84765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1171274408698082, "min": -0.10882728546857834, "max": 0.19588132202625275, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 29.164731979370117, "min": -26.118549346923828, "max": 49.949737548828125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06724828481674194, "min": -0.02268250472843647, "max": 0.5424725413322449, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.744823455810547, "min": -5.715991020202637, "max": 128.5659942626953, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06937751867420351, "min": 0.06542338193603758, "max": 0.07525062723401123, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0406627801130526, "min": 0.48319555164716915, "max": 1.0406627801130526, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009158450861286836, "min": 0.00011485621607158364, "max": 0.022044405176178877, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13737676291930254, "min": 0.0016079870250021709, "max": 0.18264860715516631, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4813575062466686e-06, "min": 7.4813575062466686e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011222036259370003, "min": 0.00011222036259370003, "max": 0.0033821036726321995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249375333333331, "min": 0.10249375333333331, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374062999999998, "min": 1.3691136000000002, "max": 2.5273678, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025912595800000004, "min": 0.00025912595800000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038868893700000004, "min": 0.0038868893700000004, "max": 0.11276404321999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.019714070484042168, "min": 0.019714070484042168, "max": 0.6492013335227966, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.29571107029914856, "min": 0.2812338173389435, "max": 4.544409275054932, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 716.3953488372093, "min": 650.046511627907, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30805.0, "min": 15984.0, "max": 32566.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.49272554922242495, "min": -1.0000000521540642, "max": 0.9947063421949427, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 21.187198616564274, "min": -32.000001668930054, "max": 46.75119808316231, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.49272554922242495, "min": -1.0000000521540642, "max": 0.9947063421949427, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 21.187198616564274, "min": -32.000001668930054, "max": 46.75119808316231, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.14619805938889122, "min": 0.1381698934697048, "max": 15.22553826496005, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.286516553722322, "min": 5.651480256579816, "max": 243.6086122393608, "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": "1784957326", "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": "1784959758" }, "total": 2432.4867179710004, "count": 1, "self": 0.5324575390004611, "children": { "run_training.setup": { "total": 0.02527817700001833, "count": 1, "self": 0.02527817700001833 }, "TrainerController.start_learning": { "total": 2431.928982255, "count": 1, "self": 1.4984568060885977, "children": { "TrainerController._reset_env": { "total": 2.516748206000102, "count": 1, "self": 2.516748206000102 }, "TrainerController.advance": { "total": 2427.824045613911, "count": 63176, "self": 1.6408984530271482, "children": { "env_step": { "total": 1760.190260463954, "count": 63176, "self": 1593.2477819318437, "children": { "SubprocessEnvManager._take_step": { "total": 166.04386810909546, "count": 63176, "self": 4.987634486064053, "children": { "TorchPolicy.evaluate": { "total": 161.0562336230314, "count": 62577, "self": 161.0562336230314 } } }, "workers": { "total": 0.8986104230148158, "count": 63176, "self": 0.0, "children": { "worker_root": { "total": 2425.9542032909944, "count": 63176, "is_parallel": true, "self": 963.3748242309875, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002142296999863902, "count": 1, "is_parallel": true, "self": 0.000753030000396393, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013892669994675089, "count": 8, "is_parallel": true, "self": 0.0013892669994675089 } } }, "UnityEnvironment.step": { "total": 0.11854425100000299, "count": 1, "is_parallel": true, "self": 0.0005195039998397988, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004639489998226054, "count": 1, "is_parallel": true, "self": 0.0004639489998226054 }, "communicator.exchange": { "total": 0.11286901300036334, "count": 1, "is_parallel": true, "self": 0.11286901300036334 }, "steps_from_proto": { "total": 0.004691784999977244, "count": 1, "is_parallel": true, "self": 0.0003458119999777409, "children": { "_process_rank_one_or_two_observation": { "total": 0.004345972999999503, "count": 8, "is_parallel": true, "self": 0.004345972999999503 } } } } } } }, "UnityEnvironment.step": { "total": 1462.5793790600069, "count": 63175, "is_parallel": true, "self": 36.50424204716728, "children": { "UnityEnvironment._generate_step_input": { "total": 26.56993042691738, "count": 63175, "is_parallel": true, "self": 26.56993042691738 }, "communicator.exchange": { "total": 1276.9301323739587, "count": 63175, "is_parallel": true, "self": 1276.9301323739587 }, "steps_from_proto": { "total": 122.57507421196351, "count": 63175, "is_parallel": true, "self": 25.43649294936813, "children": { "_process_rank_one_or_two_observation": { "total": 97.13858126259538, "count": 505400, "is_parallel": true, "self": 97.13858126259538 } } } } } } } } } } }, "trainer_advance": { "total": 665.9928866969299, "count": 63176, "self": 2.624238455005525, "children": { "process_trajectory": { "total": 116.81836021892423, "count": 63176, "self": 116.60469582492442, "children": { "RLTrainer._checkpoint": { "total": 0.21366439399980663, "count": 2, "self": 0.21366439399980663 } } }, "_update_policy": { "total": 546.5502880230001, "count": 440, "self": 291.466852947025, "children": { "TorchPPOOptimizer.update": { "total": 255.0834350759751, "count": 22809, "self": 255.0834350759751 } } } } } } }, "trainer_threads": { "total": 1.7160000425064936e-06, "count": 1, "self": 1.7160000425064936e-06 }, "TrainerController._save_models": { "total": 0.08972991300015565, "count": 1, "self": 0.0010209040001427638, "children": { "RLTrainer._checkpoint": { "total": 0.08870900900001288, "count": 1, "self": 0.08870900900001288 } } } } } } }