{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5121524930000305, "min": 0.4509446918964386, "max": 1.4445034265518188, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15446.51953125, "min": 13513.91015625, "max": 43820.45703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29876.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29876.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27204930782318115, "min": -0.11412137001752853, "max": 0.31766441464424133, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 70.188720703125, "min": -27.046764373779297, "max": 82.5927505493164, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013128106482326984, "min": 0.012554722838103771, "max": 0.32489487528800964, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.387051582336426, "min": 3.2516732215881348, "max": 77.00008392333984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06733909660316488, "min": 0.06461901827712589, "max": 0.07321716915096707, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0100864490474732, "min": 0.5469994233562878, "max": 1.0309549457651526, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014080188886469436, "min": 0.0005195293242588771, "max": 0.01421674448103368, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21120283329704154, "min": 0.00727341053962428, "max": 0.21120283329704154, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.4882375118600014e-06, "min": 2.4882375118600014e-06, "max": 9.840665159335e-05, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.732356267790002e-05, "min": 3.732356267790002e-05, "max": 0.0012110939889062, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248814, "min": 0.10248814, "max": 0.19840665000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373221000000001, "min": 1.4778860999999999, "max": 2.6110938, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002585651860000001, "min": 0.0002585651860000001, "max": 0.009840824335000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003878477790000002, "min": 0.003878477790000002, "max": 0.12112827061999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011959153227508068, "min": 0.011872670613229275, "max": 0.39796119928359985, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17938730120658875, "min": 0.1662173867225647, "max": 3.183689594268799, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 553.188679245283, "min": 523.2181818181818, "max": 997.8125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29319.0, "min": 15908.0, "max": 32773.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2580754321138814, "min": -0.9360813035164028, "max": 1.2949054272337392, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 66.67799790203571, "min": -29.95460171252489, "max": 71.21979849785566, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2580754321138814, "min": -0.9360813035164028, "max": 1.2949054272337392, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 66.67799790203571, "min": -29.95460171252489, "max": 71.21979849785566, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06713058847004881, "min": 0.06623941464329555, "max": 8.365071158623323, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5579211889125872, "min": 3.5579211889125872, "max": 133.84113853797317, "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": "1716492893", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/MyP.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 4 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716495048" }, "total": 2155.5003017950003, "count": 1, "self": 0.47679594500004896, "children": { "run_training.setup": { "total": 0.05666337299953739, "count": 1, "self": 0.05666337299953739 }, "TrainerController.start_learning": { "total": 2154.9668424770007, "count": 1, "self": 1.4137278781518035, "children": { "TrainerController._reset_env": { "total": 2.233073427999443, "count": 1, "self": 2.233073427999443 }, "TrainerController.advance": { "total": 2151.1973116418494, "count": 63427, "self": 1.4330625039374354, "children": { "env_step": { "total": 1504.1898042079856, "count": 63427, "self": 1362.8506152749533, "children": { "SubprocessEnvManager._take_step": { "total": 140.4904629920129, "count": 63427, "self": 4.8712632889091765, "children": { "TorchPolicy.evaluate": { "total": 135.61919970310373, "count": 62560, "self": 135.61919970310373 } } }, "workers": { "total": 0.8487259410194383, "count": 63427, "self": 0.0, "children": { "worker_root": { "total": 2149.679990068901, "count": 63427, "is_parallel": true, "self": 912.018402881843, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021404930002972833, "count": 1, "is_parallel": true, "self": 0.0006344759995045024, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015060170007927809, "count": 8, "is_parallel": true, "self": 0.0015060170007927809 } } }, "UnityEnvironment.step": { "total": 0.050552624000374635, "count": 1, "is_parallel": true, "self": 0.0006902699997226591, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004560980005408055, "count": 1, "is_parallel": true, "self": 0.0004560980005408055 }, "communicator.exchange": { "total": 0.04760804899979121, "count": 1, "is_parallel": true, "self": 0.04760804899979121 }, "steps_from_proto": { "total": 0.0017982070003199624, "count": 1, "is_parallel": true, "self": 0.0003975100007664878, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014006969995534746, "count": 8, "is_parallel": true, "self": 0.0014006969995534746 } } } } } } }, "UnityEnvironment.step": { "total": 1237.661587187058, "count": 63426, "is_parallel": true, "self": 34.49022878684718, "children": { "UnityEnvironment._generate_step_input": { "total": 23.742487662106214, "count": 63426, "is_parallel": true, "self": 23.742487662106214 }, "communicator.exchange": { "total": 1078.226674819146, "count": 63426, "is_parallel": true, "self": 1078.226674819146 }, "steps_from_proto": { "total": 101.20219591895875, "count": 63426, "is_parallel": true, "self": 20.623594684795535, "children": { "_process_rank_one_or_two_observation": { "total": 80.57860123416322, "count": 507408, "is_parallel": true, "self": 80.57860123416322 } } } } } } } } } } }, "trainer_advance": { "total": 645.5744449299264, "count": 63427, "self": 2.767344191974189, "children": { "process_trajectory": { "total": 132.00966931295807, "count": 63427, "self": 131.6575779329578, "children": { "RLTrainer._checkpoint": { "total": 0.3520913800002745, "count": 2, "self": 0.3520913800002745 } } }, "_update_policy": { "total": 510.7974314249941, "count": 457, "self": 291.1709916429336, "children": { "TorchPPOOptimizer.update": { "total": 219.62643978206052, "count": 22755, "self": 219.62643978206052 } } } } } } }, "trainer_threads": { "total": 1.071999577106908e-06, "count": 1, "self": 1.071999577106908e-06 }, "TrainerController._save_models": { "total": 0.12272845700044854, "count": 1, "self": 0.001923406000059913, "children": { "RLTrainer._checkpoint": { "total": 0.12080505100038863, "count": 1, "self": 0.12080505100038863 } } } } } } }