{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4969807267189026, "min": 0.42631274461746216, "max": 0.542986273765564, "count": 7 }, "Pyramids.Policy.Entropy.sum": { "value": 14694.7265625, "min": 873.0885009765625, "max": 16254.837890625, "count": 7 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "Pyramids.Step.mean": { "value": 989971.0, "min": 839959.0, "max": 989971.0, "count": 6 }, "Pyramids.Step.sum": { "value": 989971.0, "min": 839959.0, "max": 989971.0, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.25633999705314636, "min": 0.0464077964425087, "max": 0.25633999705314636, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 65.36669921875, "min": 11.509133338928223, "max": 65.36669921875, "count": 6 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007073692977428436, "min": 0.007073692977428436, "max": 0.015582084655761719, "count": 6 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8037917613983154, "min": 1.8037917613983154, "max": 3.879939079284668, "count": 6 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06593973143865924, "min": 0.06584821953645563, "max": 0.0691815057926921, "count": 6 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9231562401412292, "min": 0.7901786344374676, "max": 1.0377225868903814, "count": 6 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010510177725807996, "min": 0.006338277656357689, "max": 0.010510177725807996, "count": 6 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14714248816131195, "min": 0.08873588718900766, "max": 0.14714248816131195, "count": 6 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2788740299414286e-05, "min": 1.2788740299414286e-05, "max": 8.7043207591375e-05, "count": 6 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001790423641918, "min": 0.0001790423641918, "max": 0.0010873237825354998, "count": 6 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255772857142857, "min": 0.10255772857142857, "max": 0.117408625, "count": 6 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358082, "min": 1.4089035, "max": 1.7174645000000002, "count": 6 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026551708428571437, "min": 0.00026551708428571437, "max": 0.0017491216375000007, "count": 6 }, "Pyramids.Policy.Beta.sum": { "value": 0.003717239180000001, "min": 0.003717239180000001, "max": 0.021874703550000003, "count": 6 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011271917261183262, "min": 0.01120806485414505, "max": 0.01225132867693901, "count": 6 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15780684351921082, "min": 0.14701594412326813, "max": 0.18066348135471344, "count": 6 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 635.1132075471698, "min": 588.7083333333334, "max": 773.952380952381, "count": 6 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33661.0, "min": 22501.0, "max": 33661.0, "count": 6 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8746716693606017, "min": 0.32096186422166373, "max": 0.9086637983613826, "count": 6 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 46.35759847611189, "min": 13.480398297309875, "max": 46.35759847611189, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8746716693606017, "min": 0.32096186422166373, "max": 0.9086637983613826, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 46.35759847611189, "min": 13.480398297309875, "max": 46.35759847611189, "count": 6 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07392889281892974, "min": 0.06827661918167847, "max": 0.09641892619575151, "count": 6 }, "Pyramids.Policy.RndReward.sum": { "value": 3.918231319403276, "min": 2.90527749795001, "max": 4.049594900221564, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706806088", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706806501" }, "total": 412.98999239900013, "count": 1, "self": 0.5277990220001811, "children": { "run_training.setup": { "total": 0.045968931000061275, "count": 1, "self": 0.045968931000061275 }, "TrainerController.start_learning": { "total": 412.4162244459999, "count": 1, "self": 0.25361718202157135, "children": { "TrainerController._reset_env": { "total": 2.2507146850002755, "count": 1, "self": 2.2507146850002755 }, "TrainerController.advance": { "total": 409.8228079509777, "count": 12149, "self": 0.26849173005894045, "children": { "env_step": { "total": 288.91952816193316, "count": 12149, "self": 264.12411645289967, "children": { "SubprocessEnvManager._take_step": { "total": 24.64340950700489, "count": 12149, "self": 0.8946365079896168, "children": { "TorchPolicy.evaluate": { "total": 23.748772999015273, "count": 11939, "self": 23.748772999015273 } } }, "workers": { "total": 0.15200220202859782, "count": 12149, "self": 0.0, "children": { "worker_root": { "total": 411.31628305100185, "count": 12149, "is_parallel": true, "self": 168.8024168019865, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001999697999963246, "count": 1, "is_parallel": true, "self": 0.0006718100003126892, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013278879996505566, "count": 8, "is_parallel": true, "self": 0.0013278879996505566 } } }, "UnityEnvironment.step": { "total": 0.057077552000009746, "count": 1, "is_parallel": true, "self": 0.0006223160003173689, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005332819996510807, "count": 1, "is_parallel": true, "self": 0.0005332819996510807 }, "communicator.exchange": { "total": 0.05407051500014859, "count": 1, "is_parallel": true, "self": 0.05407051500014859 }, "steps_from_proto": { "total": 0.0018514389998927072, "count": 1, "is_parallel": true, "self": 0.0003821119989879662, "children": { "_process_rank_one_or_two_observation": { "total": 0.001469327000904741, "count": 8, "is_parallel": true, "self": 0.001469327000904741 } } } } } } }, "UnityEnvironment.step": { "total": 242.51386624901534, "count": 12148, "is_parallel": true, "self": 6.68029840002373, "children": { "UnityEnvironment._generate_step_input": { "total": 4.86561667698561, "count": 12148, "is_parallel": true, "self": 4.86561667698561 }, "communicator.exchange": { "total": 211.74738936802714, "count": 12148, "is_parallel": true, "self": 211.74738936802714 }, "steps_from_proto": { "total": 19.220561803978853, "count": 12148, "is_parallel": true, "self": 3.8417280820990527, "children": { "_process_rank_one_or_two_observation": { "total": 15.3788337218798, "count": 97184, "is_parallel": true, "self": 15.3788337218798 } } } } } } } } } } }, "trainer_advance": { "total": 120.63478805898558, "count": 12149, "self": 0.5097322969668312, "children": { "process_trajectory": { "total": 24.777226010020513, "count": 12149, "self": 24.661879365020468, "children": { "RLTrainer._checkpoint": { "total": 0.1153466450000451, "count": 1, "self": 0.1153466450000451 } } }, "_update_policy": { "total": 95.34782975199823, "count": 88, "self": 55.45195364298252, "children": { "TorchPPOOptimizer.update": { "total": 39.89587610901572, "count": 4308, "self": 39.89587610901572 } } } } } } }, "trainer_threads": { "total": 9.22000253922306e-07, "count": 1, "self": 9.22000253922306e-07 }, "TrainerController._save_models": { "total": 0.0890837060001104, "count": 1, "self": 0.0023088230000212207, "children": { "RLTrainer._checkpoint": { "total": 0.08677488300008918, "count": 1, "self": 0.08677488300008918 } } } } } } }