{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.337991327047348, "min": 0.32362666726112366, "max": 1.429599642753601, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10069.4375, "min": 9667.3759765625, "max": 43368.3359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989899.0, "min": 29952.0, "max": 989899.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989899.0, "min": 29952.0, "max": 989899.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5747349858283997, "min": -0.09383946657180786, "max": 0.6817117929458618, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.20159912109375, "min": -22.615310668945312, "max": 199.05984497070312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022336522117257118, "min": -0.023608794435858727, "max": 0.3244560956954956, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.187216758728027, "min": -6.516027450561523, "max": 76.8960952758789, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06406502446671035, "min": 0.06406502446671035, "max": 0.07326739686958582, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.896910342533945, "min": 0.5116860659894381, "max": 1.038585924857305, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01587313274363873, "min": 0.0006414991818305822, "max": 0.017217774842975007, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22222385841094222, "min": 0.00898098854562815, "max": 0.25297661428824847, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.598690324278573e-06, "min": 7.598690324278573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010638166453990002, "min": 0.00010638166453990002, "max": 0.0035071247309584994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253286428571429, "min": 0.10253286428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354601, "min": 1.3886848, "max": 2.5690415000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002630331421428572, "min": 0.0002630331421428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003682463990000001, "min": 0.003682463990000001, "max": 0.11692724584999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010160798206925392, "min": 0.010160798206925392, "max": 0.3477104604244232, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1422511786222458, "min": 0.1422511786222458, "max": 2.4339733123779297, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 331.43529411764706, "min": 284.25892857142856, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28172.0, "min": 15984.0, "max": 33695.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5744329219355302, "min": -1.0000000521540642, "max": 1.7157410600089602, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 133.82679836452007, "min": -29.348001822829247, "max": 192.16299872100353, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5744329219355302, "min": -1.0000000521540642, "max": 1.7157410600089602, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 133.82679836452007, "min": -29.348001822829247, "max": 192.16299872100353, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03498028784045292, "min": 0.0301760831732411, "max": 7.083838961087167, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9733244664384983, "min": 2.9733244664384983, "max": 113.34142337739468, "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": "1745613019", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745615364" }, "total": 2345.013278622, "count": 1, "self": 0.47705887799975244, "children": { "run_training.setup": { "total": 0.020586244000242004, "count": 1, "self": 0.020586244000242004 }, "TrainerController.start_learning": { "total": 2344.5156335, "count": 1, "self": 1.623538544976327, "children": { "TrainerController._reset_env": { "total": 2.299355853000179, "count": 1, "self": 2.299355853000179 }, "TrainerController.advance": { "total": 2340.509320675024, "count": 63915, "self": 1.7660081621447716, "children": { "env_step": { "total": 1658.5925450199084, "count": 63915, "self": 1489.9788254348564, "children": { "SubprocessEnvManager._take_step": { "total": 167.6618199039708, "count": 63915, "self": 5.039487168022333, "children": { "TorchPolicy.evaluate": { "total": 162.62233273594848, "count": 62556, "self": 162.62233273594848 } } }, "workers": { "total": 0.9518996810811586, "count": 63915, "self": 0.0, "children": { "worker_root": { "total": 2338.7097311419766, "count": 63915, "is_parallel": true, "self": 973.5214288439092, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020808320000469394, "count": 1, "is_parallel": true, "self": 0.0007549079996351793, "children": { "_process_rank_one_or_two_observation": { "total": 0.00132592400041176, "count": 8, "is_parallel": true, "self": 0.00132592400041176 } } }, "UnityEnvironment.step": { "total": 0.05006581700035895, "count": 1, "is_parallel": true, "self": 0.0005609780000668252, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004984240003977902, "count": 1, "is_parallel": true, "self": 0.0004984240003977902 }, "communicator.exchange": { "total": 0.04735191999998278, "count": 1, "is_parallel": true, "self": 0.04735191999998278 }, "steps_from_proto": { "total": 0.0016544949999115488, "count": 1, "is_parallel": true, "self": 0.0003517240002111066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013027709997004422, "count": 8, "is_parallel": true, "self": 0.0013027709997004422 } } } } } } }, "UnityEnvironment.step": { "total": 1365.1883022980674, "count": 63914, "is_parallel": true, "self": 32.937474656003815, "children": { "UnityEnvironment._generate_step_input": { "total": 24.268288141044195, "count": 63914, "is_parallel": true, "self": 24.268288141044195 }, "communicator.exchange": { "total": 1206.3647111661098, "count": 63914, "is_parallel": true, "self": 1206.3647111661098 }, "steps_from_proto": { "total": 101.61782833490952, "count": 63914, "is_parallel": true, "self": 21.380241917970125, "children": { "_process_rank_one_or_two_observation": { "total": 80.2375864169394, "count": 511312, "is_parallel": true, "self": 80.2375864169394 } } } } } } } } } } }, "trainer_advance": { "total": 680.1507674929708, "count": 63915, "self": 2.987410464995264, "children": { "process_trajectory": { "total": 134.04972926796654, "count": 63915, "self": 133.84356845096636, "children": { "RLTrainer._checkpoint": { "total": 0.20616081700018185, "count": 2, "self": 0.20616081700018185 } } }, "_update_policy": { "total": 543.113627760009, "count": 450, "self": 300.22933849297306, "children": { "TorchPPOOptimizer.update": { "total": 242.8842892670359, "count": 22818, "self": 242.8842892670359 } } } } } } }, "trainer_threads": { "total": 9.79000105871819e-07, "count": 1, "self": 9.79000105871819e-07 }, "TrainerController._save_models": { "total": 0.08341744799963635, "count": 1, "self": 0.0015959559996190364, "children": { "RLTrainer._checkpoint": { "total": 0.08182149200001732, "count": 1, "self": 0.08182149200001732 } } } } } } }