{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4000277519226074, "min": 0.3799382448196411, "max": 1.4258432388305664, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12122.44140625, "min": 11276.5673828125, "max": 43254.37890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5774335265159607, "min": -0.24216505885124207, "max": 0.5774335265159607, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.25881958007812, "min": -57.39311981201172, "max": 162.25881958007812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02499118447303772, "min": -0.011051993817090988, "max": 0.5482016801834106, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.022522926330566, "min": -3.1056103706359863, "max": 129.92379760742188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07187771852477452, "min": 0.06396740399451291, "max": 0.07609961615688601, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0062880593468433, "min": 0.5326973130982021, "max": 1.0799751049877768, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01724359222723814, "min": 0.0005666469167291975, "max": 0.017333704989151745, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24141029118133397, "min": 0.007366409917479567, "max": 0.2481308758724481, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.355947548050004e-06, "min": 7.355947548050004e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010298326567270005, "min": 0.00010298326567270005, "max": 0.0035074121308627, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245195, "min": 0.10245195, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343273, "min": 1.3886848, "max": 2.5691373, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002549498050000001, "min": 0.0002549498050000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035692972700000014, "min": 0.0035692972700000014, "max": 0.11693681627, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012382052838802338, "min": 0.012251795269548893, "max": 0.5357943177223206, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17334873974323273, "min": 0.17152513563632965, "max": 3.7505602836608887, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 316.3666666666667, "min": 316.3666666666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28473.0, "min": 15984.0, "max": 32900.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6169422074324555, "min": -1.0000000521540642, "max": 1.6181290962650805, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.524798668921, "min": -31.998001664876938, "max": 145.524798668921, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6169422074324555, "min": -1.0000000521540642, "max": 1.6181290962650805, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.524798668921, "min": -31.998001664876938, "max": 145.524798668921, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04078287829712887, "min": 0.04078287829712887, "max": 11.539565635845065, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6704590467415983, "min": 3.6704590467415983, "max": 184.63305017352104, "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": "1679204662", "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": "1679206806" }, "total": 2144.8864751660003, "count": 1, "self": 0.675539480000225, "children": { "run_training.setup": { "total": 0.18626104700001633, "count": 1, "self": 0.18626104700001633 }, "TrainerController.start_learning": { "total": 2144.0246746390003, "count": 1, "self": 1.3423647880104, "children": { "TrainerController._reset_env": { "total": 6.647812182000052, "count": 1, "self": 6.647812182000052 }, "TrainerController.advance": { "total": 2135.94234483199, "count": 63806, "self": 1.4339694910090657, "children": { "env_step": { "total": 1486.1770827589803, "count": 63806, "self": 1378.421672601049, "children": { "SubprocessEnvManager._take_step": { "total": 106.93025200899524, "count": 63806, "self": 4.8163953299847435, "children": { "TorchPolicy.evaluate": { "total": 102.1138566790105, "count": 62553, "self": 102.1138566790105 } } }, "workers": { "total": 0.8251581489359978, "count": 63806, "self": 0.0, "children": { "worker_root": { "total": 2139.3111377619225, "count": 63806, "is_parallel": true, "self": 876.8644699059255, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026809559999492194, "count": 1, "is_parallel": true, "self": 0.0008224779999181919, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018584780000310275, "count": 8, "is_parallel": true, "self": 0.0018584780000310275 } } }, "UnityEnvironment.step": { "total": 0.04771266900002047, "count": 1, "is_parallel": true, "self": 0.0005817069998101942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005073590000392869, "count": 1, "is_parallel": true, "self": 0.0005073590000392869 }, "communicator.exchange": { "total": 0.044906273000151486, "count": 1, "is_parallel": true, "self": 0.044906273000151486 }, "steps_from_proto": { "total": 0.0017173300000195013, "count": 1, "is_parallel": true, "self": 0.00042873300003520853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012885969999842928, "count": 8, "is_parallel": true, "self": 0.0012885969999842928 } } } } } } }, "UnityEnvironment.step": { "total": 1262.446667855997, "count": 63805, "is_parallel": true, "self": 31.80078452706107, "children": { "UnityEnvironment._generate_step_input": { "total": 23.644987598978787, "count": 63805, "is_parallel": true, "self": 23.644987598978787 }, "communicator.exchange": { "total": 1113.6825004580633, "count": 63805, "is_parallel": true, "self": 1113.6825004580633 }, "steps_from_proto": { "total": 93.3183952718939, "count": 63805, "is_parallel": true, "self": 19.830100314845822, "children": { "_process_rank_one_or_two_observation": { "total": 73.48829495704808, "count": 510440, "is_parallel": true, "self": 73.48829495704808 } } } } } } } } } } }, "trainer_advance": { "total": 648.3312925820007, "count": 63806, "self": 2.50510942497408, "children": { "process_trajectory": { "total": 119.78124682803059, "count": 63806, "self": 119.51918129103046, "children": { "RLTrainer._checkpoint": { "total": 0.2620655370001259, "count": 2, "self": 0.2620655370001259 } } }, "_update_policy": { "total": 526.0449363289961, "count": 453, "self": 338.09140508801624, "children": { "TorchPPOOptimizer.update": { "total": 187.95353124097983, "count": 22800, "self": 187.95353124097983 } } } } } } }, "trainer_threads": { "total": 1.0720000318542589e-06, "count": 1, "self": 1.0720000318542589e-06 }, "TrainerController._save_models": { "total": 0.09215176499992594, "count": 1, "self": 0.001391319000049407, "children": { "RLTrainer._checkpoint": { "total": 0.09076044599987654, "count": 1, "self": 0.09076044599987654 } } } } } } }