{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.304462730884552, "min": 0.299028217792511, "max": 1.4163148403167725, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9197.2099609375, "min": 8875.1572265625, "max": 42965.328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6477260589599609, "min": -0.12461249530315399, "max": 0.6683183908462524, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 190.43145751953125, "min": -29.533161163330078, "max": 190.43145751953125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02307054214179516, "min": -0.0350244976580143, "max": 0.5136933326721191, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.782739639282227, "min": -9.701786041259766, "max": 121.74532318115234, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06957311976131879, "min": 0.06429952175434057, "max": 0.07408421210191872, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0435967964197819, "min": 0.518589484713431, "max": 1.061734863081559, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014004665177910486, "min": 0.002067388477669017, "max": 0.01574181279055683, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2100699776686573, "min": 0.020967757159698647, "max": 0.22038537906779562, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.513257495613334e-06, "min": 7.513257495613334e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011269886243420001, "min": 0.00011269886243420001, "max": 0.0036307939897354006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250438666666666, "min": 0.10250438666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375657999999999, "min": 1.3886848, "max": 2.6102646000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002601882280000001, "min": 0.0002601882280000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003902823420000001, "min": 0.003902823420000001, "max": 0.12104543354, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016299718990921974, "min": 0.016299718990921974, "max": 0.6300429701805115, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24449579417705536, "min": 0.23717160522937775, "max": 4.4103007316589355, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 293.4770642201835, "min": 293.4770642201835, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31989.0, "min": 15984.0, "max": 33194.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6331009004914432, "min": -1.0000000521540642, "max": 1.6965318981637345, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 178.0079981535673, "min": -27.225001640617847, "max": 178.4133977741003, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6331009004914432, "min": -1.0000000521540642, "max": 1.6965318981637345, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 178.0079981535673, "min": -27.225001640617847, "max": 178.4133977741003, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04896778064174364, "min": 0.04896778064174364, "max": 12.931424146518111, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.337488089950057, "min": 4.96845352841774, "max": 206.90278634428978, "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": "1769053821", "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 Training3 --no-graphics", "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": "1769057449" }, "total": 3628.638995685, "count": 1, "self": 1.1980585639994388, "children": { "run_training.setup": { "total": 0.05302349399994455, "count": 1, "self": 0.05302349399994455 }, "TrainerController.start_learning": { "total": 3627.3879136270007, "count": 1, "self": 2.171162664975782, "children": { "TrainerController._reset_env": { "total": 2.935486904000072, "count": 1, "self": 2.935486904000072 }, "TrainerController.advance": { "total": 3622.1600245130244, "count": 64165, "self": 2.2672469220037783, "children": { "env_step": { "total": 2598.264390323081, "count": 64165, "self": 2371.8259663991166, "children": { "SubprocessEnvManager._take_step": { "total": 225.16596518994947, "count": 64165, "self": 6.555980498946383, "children": { "TorchPolicy.evaluate": { "total": 218.6099846910031, "count": 62574, "self": 218.6099846910031 } } }, "workers": { "total": 1.2724587340151174, "count": 64165, "self": 0.0, "children": { "worker_root": { "total": 3598.1343443691408, "count": 64165, "is_parallel": true, "self": 1452.5604791422038, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002380784000024505, "count": 1, "is_parallel": true, "self": 0.0006512020004265651, "children": { "_process_rank_one_or_two_observation": { "total": 0.00172958199959794, "count": 8, "is_parallel": true, "self": 0.00172958199959794 } } }, "UnityEnvironment.step": { "total": 0.08439524300001722, "count": 1, "is_parallel": true, "self": 0.0005523690001609793, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043442299988782906, "count": 1, "is_parallel": true, "self": 0.00043442299988782906 }, "communicator.exchange": { "total": 0.07972791900010634, "count": 1, "is_parallel": true, "self": 0.07972791900010634 }, "steps_from_proto": { "total": 0.003680531999862069, "count": 1, "is_parallel": true, "self": 0.002365908000001582, "children": { "_process_rank_one_or_two_observation": { "total": 0.001314623999860487, "count": 8, "is_parallel": true, "self": 0.001314623999860487 } } } } } } }, "UnityEnvironment.step": { "total": 2145.573865226937, "count": 64164, "is_parallel": true, "self": 48.40962821090079, "children": { "UnityEnvironment._generate_step_input": { "total": 24.414565838018007, "count": 64164, "is_parallel": true, "self": 24.414565838018007 }, "communicator.exchange": { "total": 1876.1557742769812, "count": 64164, "is_parallel": true, "self": 1876.1557742769812 }, "steps_from_proto": { "total": 196.59389690103694, "count": 64164, "is_parallel": true, "self": 53.527349632193136, "children": { "_process_rank_one_or_two_observation": { "total": 143.0665472688438, "count": 513312, "is_parallel": true, "self": 143.0665472688438 } } } } } } } } } } }, "trainer_advance": { "total": 1021.6283872679396, "count": 64165, "self": 4.172536632953779, "children": { "process_trajectory": { "total": 195.83578177498566, "count": 64165, "self": 195.5771347039854, "children": { "RLTrainer._checkpoint": { "total": 0.2586470710002686, "count": 2, "self": 0.2586470710002686 } } }, "_update_policy": { "total": 821.6200688600002, "count": 457, "self": 498.33796606796136, "children": { "TorchPPOOptimizer.update": { "total": 323.2821027920388, "count": 22773, "self": 323.2821027920388 } } } } } } }, "trainer_threads": { "total": 1.3170001693652011e-06, "count": 1, "self": 1.3170001693652011e-06 }, "TrainerController._save_models": { "total": 0.12123822800003836, "count": 1, "self": 0.0013147399995432352, "children": { "RLTrainer._checkpoint": { "total": 0.11992348800049513, "count": 1, "self": 0.11992348800049513 } } } } } } }