{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6024505496025085, "min": 0.6024505496025085, "max": 1.4493601322174072, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 18083.15625, "min": 18083.15625, "max": 43967.7890625, "count": 10 }, "Pyramids.Step.mean": { "value": 299991.0, "min": 29952.0, "max": 299991.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299991.0, "min": 29952.0, "max": 299991.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06579789519309998, "min": -0.09317436069250107, "max": 0.059849321842193604, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -15.857293128967285, "min": -22.455020904541016, "max": 14.18428897857666, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.12189578264951706, "min": 0.1146334707736969, "max": 0.2834940552711487, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 29.37688446044922, "min": 27.626667022705078, "max": 68.03857421875, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07094410641918318, "min": 0.0678833937407797, "max": 0.07255747662202937, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9932174898685646, "min": 0.49977608782609917, "max": 0.9932174898685646, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0015121206146295055, "min": 0.0009696979949006182, "max": 0.006057562782178598, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.021169688604813077, "min": 0.006787885964304328, "max": 0.04240293947525019, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4777952216904762e-05, "min": 1.4777952216904762e-05, "max": 0.0002838354339596191, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00020689133103666667, "min": 0.00020689133103666667, "max": 0.0023495984168006665, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10492595238095238, "min": 0.10492595238095238, "max": 0.19461180952380958, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4689633333333334, "min": 1.2970453333333334, "max": 1.983199333333333, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005021026428571428, "min": 0.0005021026428571428, "max": 0.00946171977142857, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.0070294369999999995, "min": 0.0070294369999999995, "max": 0.0783616134, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.12291280180215836, "min": 0.11343616247177124, "max": 0.46290522813796997, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.7207791805267334, "min": 1.2829687595367432, "max": 3.2403366565704346, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 965.5483870967741, "min": 947.8787878787879, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29932.0, "min": 15984.0, "max": 32372.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7725613386400284, "min": -1.0000000521540642, "max": -0.5781185662856808, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -23.94940149784088, "min": -32.000001668930054, "max": -15.609201289713383, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7725613386400284, "min": -1.0000000521540642, "max": -0.5781185662856808, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -23.94940149784088, "min": -32.000001668930054, "max": -15.609201289713383, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 1.1563665619300258, "min": 1.1062247881200165, "max": 8.775965873152018, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 35.8473634198308, "min": 30.762977307662368, "max": 140.41545397043228, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1788623021", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788624004" }, "total": 983.4330367889997, "count": 1, "self": 0.6904221729996607, "children": { "run_training.setup": { "total": 0.030382818000362022, "count": 1, "self": 0.030382818000362022 }, "TrainerController.start_learning": { "total": 982.7122317979997, "count": 1, "self": 0.660775411978193, "children": { "TrainerController._reset_env": { "total": 2.852162200999828, "count": 1, "self": 2.852162200999828 }, "TrainerController.advance": { "total": 979.0669936700219, "count": 18882, "self": 0.7042802610103536, "children": { "env_step": { "total": 653.9170312740016, "count": 18882, "self": 605.0100384649754, "children": { "SubprocessEnvManager._take_step": { "total": 48.4974534259909, "count": 18882, "self": 2.139900238944847, "children": { "TorchPolicy.evaluate": { "total": 46.35755318704605, "count": 18801, "self": 46.35755318704605 } } }, "workers": { "total": 0.4095393830352805, "count": 18882, "self": 0.0, "children": { "worker_root": { "total": 980.0396467129767, "count": 18882, "is_parallel": true, "self": 431.1060518819654, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030979379998825607, "count": 1, "is_parallel": true, "self": 0.0010762459996840334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020216920001985272, "count": 8, "is_parallel": true, "self": 0.0020216920001985272 } } }, "UnityEnvironment.step": { "total": 0.06605351300004259, "count": 1, "is_parallel": true, "self": 0.0006469440004366334, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005974229998173541, "count": 1, "is_parallel": true, "self": 0.0005974229998173541 }, "communicator.exchange": { "total": 0.06267427600005249, "count": 1, "is_parallel": true, "self": 0.06267427600005249 }, "steps_from_proto": { "total": 0.002134869999736111, "count": 1, "is_parallel": true, "self": 0.0004263109999556036, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017085589997805073, "count": 8, "is_parallel": true, "self": 0.0017085589997805073 } } } } } } }, "UnityEnvironment.step": { "total": 548.9335948310113, "count": 18881, "is_parallel": true, "self": 13.816866547022528, "children": { "UnityEnvironment._generate_step_input": { "total": 9.817664533976313, "count": 18881, "is_parallel": true, "self": 9.817664533976313 }, "communicator.exchange": { "total": 480.61411761601494, "count": 18881, "is_parallel": true, "self": 480.61411761601494 }, "steps_from_proto": { "total": 44.68494613399753, "count": 18881, "is_parallel": true, "self": 8.812037435983257, "children": { "_process_rank_one_or_two_observation": { "total": 35.87290869801427, "count": 151048, "is_parallel": true, "self": 35.87290869801427 } } } } } } } } } } }, "trainer_advance": { "total": 324.44568213501, "count": 18882, "self": 1.1112439099561016, "children": { "process_trajectory": { "total": 44.15237628805562, "count": 18882, "self": 44.15237628805562 }, "_update_policy": { "total": 279.18206193699825, "count": 113, "self": 106.66588109899567, "children": { "TorchPPOOptimizer.update": { "total": 172.51618083800258, "count": 6885, "self": 172.51618083800258 } } } } } } }, "trainer_threads": { "total": 1.0469998414919246e-06, "count": 1, "self": 1.0469998414919246e-06 }, "TrainerController._save_models": { "total": 0.1322994679999283, "count": 1, "self": 0.0020758840000780765, "children": { "RLTrainer._checkpoint": { "total": 0.13022358399985023, "count": 1, "self": 0.13022358399985023 } } } } } } }