{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4738803803920746, "min": 0.4738803803920746, "max": 1.4607224464416504, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14413.5458984375, "min": 14120.5009765625, "max": 44312.4765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29940.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29940.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5412266850471497, "min": -0.13136444985866547, "max": 0.6165623068809509, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.16714477539062, "min": -31.527467727661133, "max": 170.7039794921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02286222204566002, "min": -0.004147015977650881, "max": 0.3554820120334625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.470008850097656, "min": -1.1196943521499634, "max": 84.60472106933594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06751539292862686, "min": 0.06560502753236581, "max": 0.0734383504443341, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.945215501000776, "min": 0.4794338138087588, "max": 1.0573242691558942, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015086740736302751, "min": 0.0001971077924592591, "max": 0.01669634478873507, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2112143703082385, "min": 0.002365293509511109, "max": 0.23374882704229094, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.711061715392855e-06, "min": 7.711061715392855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010795486401549996, "min": 0.00010795486401549996, "max": 0.0036088143970618987, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257032142857145, "min": 0.10257032142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359845000000002, "min": 1.3886848, "max": 2.6174056, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026677511071428563, "min": 0.00026677511071428563, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003734851549999999, "min": 0.003734851549999999, "max": 0.12030351618999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009258056990802288, "min": 0.009258056990802288, "max": 0.42740482091903687, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12961280345916748, "min": 0.12961280345916748, "max": 2.9918336868286133, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 318.3578947368421, "min": 313.13978494623655, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30244.0, "min": 17634.0, "max": 32124.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6395284006470128, "min": -0.9998875521123409, "max": 1.6438386901732414, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 155.75519806146622, "min": -31.99640166759491, "max": 155.75519806146622, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6395284006470128, "min": -0.9998875521123409, "max": 1.6438386901732414, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 155.75519806146622, "min": -31.99640166759491, "max": 155.75519806146622, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03104400059306308, "min": 0.03104400059306308, "max": 7.738087490200996, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9491800563409925, "min": 2.9491800563409925, "max": 139.28557482361794, "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": "1680815077", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680817319" }, "total": 2242.312401243, "count": 1, "self": 0.5862385919999724, "children": { "run_training.setup": { "total": 0.1830759209997268, "count": 1, "self": 0.1830759209997268 }, "TrainerController.start_learning": { "total": 2241.54308673, "count": 1, "self": 1.4299370100425222, "children": { "TrainerController._reset_env": { "total": 5.005564408000282, "count": 1, "self": 5.005564408000282 }, "TrainerController.advance": { "total": 2235.012954189958, "count": 63833, "self": 1.4810279728708338, "children": { "env_step": { "total": 1611.9200069169974, "count": 63833, "self": 1500.423559084994, "children": { "SubprocessEnvManager._take_step": { "total": 110.62071218597794, "count": 63833, "self": 4.937781984981484, "children": { "TorchPolicy.evaluate": { "total": 105.68293020099645, "count": 62560, "self": 105.68293020099645 } } }, "workers": { "total": 0.8757356460255323, "count": 63833, "self": 0.0, "children": { "worker_root": { "total": 2236.30132122501, "count": 63833, "is_parallel": true, "self": 853.1551611910945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002823130999786372, "count": 1, "is_parallel": true, "self": 0.000895879000381683, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019272519994046888, "count": 8, "is_parallel": true, "self": 0.0019272519994046888 } } }, "UnityEnvironment.step": { "total": 0.04936992500006454, "count": 1, "is_parallel": true, "self": 0.0005599539990726043, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000500226000440307, "count": 1, "is_parallel": true, "self": 0.000500226000440307 }, "communicator.exchange": { "total": 0.04666081499999564, "count": 1, "is_parallel": true, "self": 0.04666081499999564 }, "steps_from_proto": { "total": 0.0016489300005559926, "count": 1, "is_parallel": true, "self": 0.0003926430026695016, "children": { "_process_rank_one_or_two_observation": { "total": 0.001256286997886491, "count": 8, "is_parallel": true, "self": 0.001256286997886491 } } } } } } }, "UnityEnvironment.step": { "total": 1383.1461600339153, "count": 63832, "is_parallel": true, "self": 33.43392795415639, "children": { "UnityEnvironment._generate_step_input": { "total": 24.96604650007248, "count": 63832, "is_parallel": true, "self": 24.96604650007248 }, "communicator.exchange": { "total": 1223.3712738188997, "count": 63832, "is_parallel": true, "self": 1223.3712738188997 }, "steps_from_proto": { "total": 101.37491176078674, "count": 63832, "is_parallel": true, "self": 22.040230308604805, "children": { "_process_rank_one_or_two_observation": { "total": 79.33468145218194, "count": 510656, "is_parallel": true, "self": 79.33468145218194 } } } } } } } } } } }, "trainer_advance": { "total": 621.6119193000895, "count": 63833, "self": 2.5367783892424995, "children": { "process_trajectory": { "total": 110.94901360384392, "count": 63833, "self": 110.73724940084321, "children": { "RLTrainer._checkpoint": { "total": 0.21176420300071186, "count": 2, "self": 0.21176420300071186 } } }, "_update_policy": { "total": 508.1261273070031, "count": 453, "self": 325.4129669689728, "children": { "TorchPPOOptimizer.update": { "total": 182.71316033803032, "count": 22794, "self": 182.71316033803032 } } } } } } }, "trainer_threads": { "total": 9.489995136391371e-07, "count": 1, "self": 9.489995136391371e-07 }, "TrainerController._save_models": { "total": 0.0946301730000414, "count": 1, "self": 0.0014569019995178678, "children": { "RLTrainer._checkpoint": { "total": 0.09317327100052353, "count": 1, "self": 0.09317327100052353 } } } } } } }