{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4160597324371338, "min": 0.41000181436538696, "max": 1.4275988340377808, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12488.44921875, "min": 12365.654296875, "max": 43307.63671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.37501418590545654, "min": -0.09309344738721848, "max": 0.44914954900741577, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 100.1287841796875, "min": -22.621707916259766, "max": 121.27037811279297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04570809006690979, "min": -0.04570809006690979, "max": 0.2590528130531311, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -12.204059600830078, "min": -12.204059600830078, "max": 62.69078063964844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06531804534781639, "min": 0.06531804534781639, "max": 0.07585901989412605, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9797706802172459, "min": 0.5139883715139526, "max": 1.0687320317180518, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015245630311379451, "min": 0.0003391035980108824, "max": 0.015979506661453487, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22868445467069176, "min": 0.0037301395781197066, "max": 0.22868445467069176, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.442237519286666e-06, "min": 7.442237519286666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011163356278929999, "min": 0.00011163356278929999, "max": 0.0036334855888381997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248071333333333, "min": 0.10248071333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372107, "min": 1.3886848, "max": 2.6174889, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025782326200000005, "min": 0.00025782326200000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038673489300000007, "min": 0.0038673489300000007, "max": 0.12113506382, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012100035324692726, "min": 0.012100035324692726, "max": 0.3591423034667969, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18150052428245544, "min": 0.17454278469085693, "max": 2.513996124267578, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 474.8181818181818, "min": 411.8857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31338.0, "min": 15984.0, "max": 32881.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.275421521296868, "min": -1.0000000521540642, "max": 1.4738028335784163, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 82.90239888429642, "min": -30.9994016289711, "max": 103.90219834446907, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.275421521296868, "min": -1.0000000521540642, "max": 1.4738028335784163, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 82.90239888429642, "min": -30.9994016289711, "max": 103.90219834446907, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05932005439737203, "min": 0.05412491475532002, "max": 7.043049892410636, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.855803535829182, "min": 3.8428689476277214, "max": 112.68879827857018, "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": "1710775404", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710777801" }, "total": 2396.134726698, "count": 1, "self": 0.526806365000084, "children": { "run_training.setup": { "total": 0.08075364100000115, "count": 1, "self": 0.08075364100000115 }, "TrainerController.start_learning": { "total": 2395.527166692, "count": 1, "self": 1.8573782059802397, "children": { "TrainerController._reset_env": { "total": 2.753445645000056, "count": 1, "self": 2.753445645000056 }, "TrainerController.advance": { "total": 2390.8197272420193, "count": 63607, "self": 1.9235792290019162, "children": { "env_step": { "total": 1732.1908262839895, "count": 63607, "self": 1570.683946147973, "children": { "SubprocessEnvManager._take_step": { "total": 160.36770279995608, "count": 63607, "self": 5.971909600038089, "children": { "TorchPolicy.evaluate": { "total": 154.395793199918, "count": 62555, "self": 154.395793199918 } } }, "workers": { "total": 1.1391773360603565, "count": 63607, "self": 0.0, "children": { "worker_root": { "total": 2389.4616662079843, "count": 63607, "is_parallel": true, "self": 965.1758695659632, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033365949998369615, "count": 1, "is_parallel": true, "self": 0.0008208860003833252, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025157089994536364, "count": 8, "is_parallel": true, "self": 0.0025157089994536364 } } }, "UnityEnvironment.step": { "total": 0.061527974999989965, "count": 1, "is_parallel": true, "self": 0.0006853090001186501, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005141479998655996, "count": 1, "is_parallel": true, "self": 0.0005141479998655996 }, "communicator.exchange": { "total": 0.05793639000012263, "count": 1, "is_parallel": true, "self": 0.05793639000012263 }, "steps_from_proto": { "total": 0.002392127999883087, "count": 1, "is_parallel": true, "self": 0.000514051999516596, "children": { "_process_rank_one_or_two_observation": { "total": 0.001878076000366491, "count": 8, "is_parallel": true, "self": 0.001878076000366491 } } } } } } }, "UnityEnvironment.step": { "total": 1424.285796642021, "count": 63606, "is_parallel": true, "self": 39.38268684097693, "children": { "UnityEnvironment._generate_step_input": { "total": 26.881180477027783, "count": 63606, "is_parallel": true, "self": 26.881180477027783 }, "communicator.exchange": { "total": 1243.628377631996, "count": 63606, "is_parallel": true, "self": 1243.628377631996 }, "steps_from_proto": { "total": 114.39355169202031, "count": 63606, "is_parallel": true, "self": 24.37391511312785, "children": { "_process_rank_one_or_two_observation": { "total": 90.01963657889246, "count": 508848, "is_parallel": true, "self": 90.01963657889246 } } } } } } } } } } }, "trainer_advance": { "total": 656.7053217290281, "count": 63607, "self": 3.5795271760898686, "children": { "process_trajectory": { "total": 136.9085428089436, "count": 63607, "self": 136.6912218579439, "children": { "RLTrainer._checkpoint": { "total": 0.2173209509996923, "count": 2, "self": 0.2173209509996923 } } }, "_update_policy": { "total": 516.2172517439947, "count": 453, "self": 302.8976526409465, "children": { "TorchPPOOptimizer.update": { "total": 213.31959910304818, "count": 22791, "self": 213.31959910304818 } } } } } } }, "trainer_threads": { "total": 9.949999366654083e-07, "count": 1, "self": 9.949999366654083e-07 }, "TrainerController._save_models": { "total": 0.09661460400002397, "count": 1, "self": 0.0015241600003719213, "children": { "RLTrainer._checkpoint": { "total": 0.09509044399965205, "count": 1, "self": 0.09509044399965205 } } } } } } }