{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.011104866862297058, "min": 0.003307957900688052, "max": 1.369984745979309, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 335.8111877441406, "min": 99.39752197265625, "max": 41559.85546875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999974.0, "min": 29902.0, "max": 2999974.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999974.0, "min": 29902.0, "max": 2999974.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0923529639840126, "min": -0.1672210991382599, "max": -0.07027246057987213, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -22.257064819335938, "min": -40.467506408691406, "max": -16.86539077758789, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 5.13019323348999, "min": 0.8507001399993896, "max": 5.13019323348999, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1236.3765869140625, "min": 201.61593627929688, "max": 1236.3765869140625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07041475831361119, "min": 0.062510486157687, "max": 0.07574947997784776, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9153918580769455, "min": 0.5302463598449343, "max": 0.9525683969597389, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015404913683460652, "min": 0.008987323909905861, "max": 0.03702300083321234, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20026387788498848, "min": 0.1168352108287762, "max": 0.35007711305044875, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5570994809999983e-06, "min": 1.5570994809999983e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0242293252999978e-05, "min": 2.0242293252999978e-05, "max": 0.003366679677773466, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051900000000001, "min": 0.10051900000000001, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.306747, "min": 1.2421028, "max": 2.3724954000000005, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.184809999999995e-05, "min": 6.184809999999995e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008040252999999993, "min": 0.0008040252999999993, "max": 0.11223043067999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 5.074411869049072, "min": 1.4162445068359375, "max": 5.124239444732666, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 65.96735382080078, "min": 9.913711547851562, "max": 66.1933822631836, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 996.9354838709677, "min": 951.258064516129, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30905.0, "min": 16829.0, "max": 32852.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9332194035091708, "min": -0.9999871489501768, "max": -0.769530052319169, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -28.929801508784294, "min": -31.998401671648026, "max": -14.845000892877579, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9332194035091708, "min": -0.9999871489501768, "max": -0.769530052319169, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -28.929801508784294, "min": -31.998401671648026, "max": -14.845000892877579, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 50.61364495754242, "min": 20.102847195440724, "max": 51.51651854813099, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1569.022993683815, "min": 355.1764689683914, "max": 1648.5285935401917, "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": "1752647417", "python_version": "3.10.12 (main, May 27 2025, 17:12:29) [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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752656248" }, "total": 8831.09914089, "count": 1, "self": 0.5788933980020374, "children": { "run_training.setup": { "total": 0.02245575300003111, "count": 1, "self": 0.02245575300003111 }, "TrainerController.start_learning": { "total": 8830.497791738999, "count": 1, "self": 5.856917507286198, "children": { "TrainerController._reset_env": { "total": 2.3155528509996657, "count": 1, "self": 2.3155528509996657 }, "TrainerController.advance": { "total": 8822.254458356714, "count": 188154, "self": 6.1813940836145775, "children": { "env_step": { "total": 4596.256905358199, "count": 188154, "self": 4141.1522924663495, "children": { "SubprocessEnvManager._take_step": { "total": 451.3759023913681, "count": 188154, "self": 18.671619549968455, "children": { "TorchPolicy.evaluate": { "total": 432.7042828413996, "count": 187561, "self": 432.7042828413996 } } }, "workers": { "total": 3.7287105004816112, "count": 188154, "self": 0.0, "children": { "worker_root": { "total": 8811.494612228104, "count": 188154, "is_parallel": true, "self": 5129.136559922052, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004119294999327394, "count": 1, "is_parallel": true, "self": 0.0009720319985717651, "children": { "_process_rank_one_or_two_observation": { "total": 0.003147263000755629, "count": 8, "is_parallel": true, "self": 0.003147263000755629 } } }, "UnityEnvironment.step": { "total": 0.05682411000088905, "count": 1, "is_parallel": true, "self": 0.0006210379997355631, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005320100008248119, "count": 1, "is_parallel": true, "self": 0.0005320100008248119 }, "communicator.exchange": { "total": 0.053775569000208634, "count": 1, "is_parallel": true, "self": 0.053775569000208634 }, "steps_from_proto": { "total": 0.001895493000120041, "count": 1, "is_parallel": true, "self": 0.0004048139999213163, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014906790001987247, "count": 8, "is_parallel": true, "self": 0.0014906790001987247 } } } } } } }, "UnityEnvironment.step": { "total": 3682.358052306052, "count": 188153, "is_parallel": true, "self": 123.97461927842596, "children": { "UnityEnvironment._generate_step_input": { "total": 85.04629777959053, "count": 188153, "is_parallel": true, "self": 85.04629777959053 }, "communicator.exchange": { "total": 3110.438054400821, "count": 188153, "is_parallel": true, "self": 3110.438054400821 }, "steps_from_proto": { "total": 362.89908084721446, "count": 188153, "is_parallel": true, "self": 75.75954596979682, "children": { "_process_rank_one_or_two_observation": { "total": 287.13953487741765, "count": 1505224, "is_parallel": true, "self": 287.13953487741765 } } } } } } } } } } }, "trainer_advance": { "total": 4219.8161589148995, "count": 188154, "self": 9.145347010502519, "children": { "process_trajectory": { "total": 438.04848791341465, "count": 188154, "self": 437.583755714415, "children": { "RLTrainer._checkpoint": { "total": 0.46473219899962714, "count": 6, "self": 0.46473219899962714 } } }, "_update_policy": { "total": 3772.6223239909823, "count": 1214, "self": 1042.7769611561753, "children": { "TorchPPOOptimizer.update": { "total": 2729.845362834807, "count": 68712, "self": 2729.845362834807 } } } } } } }, "trainer_threads": { "total": 1.0309995559509844e-06, "count": 1, "self": 1.0309995559509844e-06 }, "TrainerController._save_models": { "total": 0.07086199299919826, "count": 1, "self": 0.0017644909985392587, "children": { "RLTrainer._checkpoint": { "total": 0.069097502000659, "count": 1, "self": 0.069097502000659 } } } } } } }