{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5588542819023132, "min": 0.551475465297699, "max": 1.4994239807128906, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16783.51171875, "min": 16314.849609375, "max": 45486.52734375, "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": 0.26304951310157776, "min": -0.2972862720489502, "max": 0.3033043146133423, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 66.8145751953125, "min": -70.45684814453125, "max": 79.16242980957031, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0022037788294255733, "min": -0.032758623361587524, "max": 0.349622517824173, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.559759795665741, "min": -8.255172729492188, "max": 82.86053466796875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07021579878591915, "min": 0.06387294853848481, "max": 0.07571913160764022, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0532369817887872, "min": 0.5245881236195779, "max": 1.0532369817887872, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010137469942532739, "min": 0.00022632723707559143, "max": 0.012744551067785439, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1520620491379911, "min": 0.0029422540819826885, "max": 0.17842371494899614, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.518737493786663e-06, "min": 7.518737493786663e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011278106240679995, "min": 0.00011278106240679995, "max": 0.0033699007766997994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250621333333335, "min": 0.10250621333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375932, "min": 1.3886848, "max": 2.4434124000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026037071199999987, "min": 0.00026037071199999987, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039055606799999983, "min": 0.0039055606799999983, "max": 0.11234768998000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00693019712343812, "min": 0.00693019712343812, "max": 0.33072519302368164, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10395295917987823, "min": 0.10054250061511993, "max": 2.3150763511657715, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 582.5961538461538, "min": 535.1607142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30295.0, "min": 15984.0, "max": 33423.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9172576578477254, "min": -1.0000000521540642, "max": 1.168783640679048, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 47.69739820808172, "min": -29.930001698434353, "max": 60.02559797465801, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9172576578477254, "min": -1.0000000521540642, "max": 1.168783640679048, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 47.69739820808172, "min": -29.930001698434353, "max": 60.02559797465801, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04182591868587993, "min": 0.04043102273940998, "max": 7.33909232635051, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1749477716657566, "min": 2.1749477716657566, "max": 117.42547722160816, "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": "1728371422", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728373588" }, "total": 2166.9267952929995, "count": 1, "self": 0.4774657839993779, "children": { "run_training.setup": { "total": 0.08009313299999121, "count": 1, "self": 0.08009313299999121 }, "TrainerController.start_learning": { "total": 2166.369236376, "count": 1, "self": 1.3791560459821994, "children": { "TrainerController._reset_env": { "total": 2.442108112999904, "count": 1, "self": 2.442108112999904 }, "TrainerController.advance": { "total": 2162.461276580018, "count": 63429, "self": 1.3354987350935517, "children": { "env_step": { "total": 1461.096447198995, "count": 63429, "self": 1308.3559718570373, "children": { "SubprocessEnvManager._take_step": { "total": 151.94399579904393, "count": 63429, "self": 4.538589670901729, "children": { "TorchPolicy.evaluate": { "total": 147.4054061281422, "count": 62559, "self": 147.4054061281422 } } }, "workers": { "total": 0.7964795429138576, "count": 63429, "self": 0.0, "children": { "worker_root": { "total": 2161.5878371790573, "count": 63429, "is_parallel": true, "self": 968.7519943860475, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029344740000851743, "count": 1, "is_parallel": true, "self": 0.0008366899996872235, "children": { "_process_rank_one_or_two_observation": { "total": 0.002097784000397951, "count": 8, "is_parallel": true, "self": 0.002097784000397951 } } }, "UnityEnvironment.step": { "total": 0.0500487819999762, "count": 1, "is_parallel": true, "self": 0.0006837619998805167, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044564700010596425, "count": 1, "is_parallel": true, "self": 0.00044564700010596425 }, "communicator.exchange": { "total": 0.0473112729996501, "count": 1, "is_parallel": true, "self": 0.0473112729996501 }, "steps_from_proto": { "total": 0.0016081000003396184, "count": 1, "is_parallel": true, "self": 0.000343535000411066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012645649999285524, "count": 8, "is_parallel": true, "self": 0.0012645649999285524 } } } } } } }, "UnityEnvironment.step": { "total": 1192.8358427930098, "count": 63428, "is_parallel": true, "self": 33.539452343953144, "children": { "UnityEnvironment._generate_step_input": { "total": 23.146865097011414, "count": 63428, "is_parallel": true, "self": 23.146865097011414 }, "communicator.exchange": { "total": 1039.3944780850302, "count": 63428, "is_parallel": true, "self": 1039.3944780850302 }, "steps_from_proto": { "total": 96.75504726701502, "count": 63428, "is_parallel": true, "self": 19.491244454006846, "children": { "_process_rank_one_or_two_observation": { "total": 77.26380281300817, "count": 507424, "is_parallel": true, "self": 77.26380281300817 } } } } } } } } } } }, "trainer_advance": { "total": 700.0293306459293, "count": 63429, "self": 2.575815916902229, "children": { "process_trajectory": { "total": 130.7592322420237, "count": 63429, "self": 130.5627587280237, "children": { "RLTrainer._checkpoint": { "total": 0.19647351399999025, "count": 2, "self": 0.19647351399999025 } } }, "_update_policy": { "total": 566.6942824870034, "count": 446, "self": 321.5970998759685, "children": { "TorchPPOOptimizer.update": { "total": 245.0971826110349, "count": 22755, "self": 245.0971826110349 } } } } } } }, "trainer_threads": { "total": 1.020999661704991e-06, "count": 1, "self": 1.020999661704991e-06 }, "TrainerController._save_models": { "total": 0.0866946160003863, "count": 1, "self": 0.0014936180004951893, "children": { "RLTrainer._checkpoint": { "total": 0.08520099799989111, "count": 1, "self": 0.08520099799989111 } } } } } } }