{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3973802328109741, "min": 0.3973802328109741, "max": 1.3802801370620728, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11870.5419921875, "min": 11870.5419921875, "max": 41872.1796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5942457914352417, "min": -0.10642901062965393, "max": 0.6251446008682251, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.76580810546875, "min": -25.755821228027344, "max": 173.79019165039062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014014225453138351, "min": -0.02560507133603096, "max": 0.4442564845085144, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.9800400733947754, "min": -6.990184307098389, "max": 105.28878784179688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06763658930195246, "min": 0.06489695645222028, "max": 0.0708255997214092, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.014548839529287, "min": 0.4620946203833499, "max": 1.0391342208244811, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01630923163965253, "min": 0.0007117490694123321, "max": 0.016963665547553408, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24463847459478794, "min": 0.008172227067989715, "max": 0.25154309093669125, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.565917478060002e-06, "min": 7.565917478060002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011348876217090004, "min": 0.00011348876217090004, "max": 0.0036325990891336994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252194, "min": 0.10252194, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378291000000002, "min": 1.3691136000000002, "max": 2.6108663, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026194180600000005, "min": 0.00026194180600000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003929127090000001, "min": 0.003929127090000001, "max": 0.12110554336999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011991094797849655, "min": 0.011421384289860725, "max": 0.5160561800003052, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17986641824245453, "min": 0.15989938378334045, "max": 3.612393379211426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 323.03921568627453, "min": 299.6185567010309, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32950.0, "min": 15984.0, "max": 32950.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5984941076706438, "min": -1.0000000521540642, "max": 1.6591278138695305, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.04639898240566, "min": -32.000001668930054, "max": 163.04639898240566, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5984941076706438, "min": -1.0000000521540642, "max": 1.6591278138695305, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.04639898240566, "min": -32.000001668930054, "max": 163.04639898240566, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03991840862680892, "min": 0.03991840862680892, "max": 10.244121041148901, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.07167767993451, "min": 3.550219074895722, "max": 163.90593665838242, "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": "1691619906", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691622835" }, "total": 2929.568766831, "count": 1, "self": 0.526970478000294, "children": { "run_training.setup": { "total": 0.046655310000005557, "count": 1, "self": 0.046655310000005557 }, "TrainerController.start_learning": { "total": 2928.995141043, "count": 1, "self": 2.1222044580308648, "children": { "TrainerController._reset_env": { "total": 4.62462242599986, "count": 1, "self": 4.62462242599986 }, "TrainerController.advance": { "total": 2922.139043443969, "count": 63959, "self": 2.048368900951573, "children": { "env_step": { "total": 2134.575959725017, "count": 63959, "self": 1982.2691949179957, "children": { "SubprocessEnvManager._take_step": { "total": 151.06971333604542, "count": 63959, "self": 6.335280775055708, "children": { "TorchPolicy.evaluate": { "total": 144.73443256098972, "count": 62569, "self": 144.73443256098972 } } }, "workers": { "total": 1.2370514709759846, "count": 63959, "self": 0.0, "children": { "worker_root": { "total": 2921.758912515976, "count": 63959, "is_parallel": true, "self": 1094.760855046925, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019740490001822764, "count": 1, "is_parallel": true, "self": 0.0005981340000289492, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013759150001533271, "count": 8, "is_parallel": true, "self": 0.0013759150001533271 } } }, "UnityEnvironment.step": { "total": 0.05466381899987027, "count": 1, "is_parallel": true, "self": 0.0006909279998126294, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005517659999441094, "count": 1, "is_parallel": true, "self": 0.0005517659999441094 }, "communicator.exchange": { "total": 0.051206370000045354, "count": 1, "is_parallel": true, "self": 0.051206370000045354 }, "steps_from_proto": { "total": 0.0022147550000681804, "count": 1, "is_parallel": true, "self": 0.0004068739997364901, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018078810003316903, "count": 8, "is_parallel": true, "self": 0.0018078810003316903 } } } } } } }, "UnityEnvironment.step": { "total": 1826.9980574690512, "count": 63958, "is_parallel": true, "self": 44.001148512051486, "children": { "UnityEnvironment._generate_step_input": { "total": 28.30416076399638, "count": 63958, "is_parallel": true, "self": 28.30416076399638 }, "communicator.exchange": { "total": 1618.6651091809879, "count": 63958, "is_parallel": true, "self": 1618.6651091809879 }, "steps_from_proto": { "total": 136.02763901201547, "count": 63958, "is_parallel": true, "self": 28.229608861063298, "children": { "_process_rank_one_or_two_observation": { "total": 107.79803015095217, "count": 511664, "is_parallel": true, "self": 107.79803015095217 } } } } } } } } } } }, "trainer_advance": { "total": 785.5147148180004, "count": 63959, "self": 3.747279301941262, "children": { "process_trajectory": { "total": 133.28388302405983, "count": 63959, "self": 132.97573073305966, "children": { "RLTrainer._checkpoint": { "total": 0.3081522910001695, "count": 2, "self": 0.3081522910001695 } } }, "_update_policy": { "total": 648.4835524919993, "count": 450, "self": 420.8598343430283, "children": { "TorchPPOOptimizer.update": { "total": 227.62371814897097, "count": 22767, "self": 227.62371814897097 } } } } } } }, "trainer_threads": { "total": 1.3280005077831447e-06, "count": 1, "self": 1.3280005077831447e-06 }, "TrainerController._save_models": { "total": 0.10926938699958555, "count": 1, "self": 0.0016629060000923346, "children": { "RLTrainer._checkpoint": { "total": 0.10760648099949321, "count": 1, "self": 0.10760648099949321 } } } } } } }