{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.927981376647949, "min": 3.8751437664031982, "max": 4.380889415740967, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 21741.376953125, "min": 6804.640625, "max": 28357.529296875, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8925924428083278, "min": 0.5888889440231853, "max": 0.8999999215205511, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 24.099995955824852, "min": 7.500000648200512, "max": 31.899996653199196, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 121.29669867621527, "min": 10.817269179556105, "max": 175.8681265513102, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 3275.0108642578125, "min": 251.57147407531738, "max": 3275.0108642578125, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.3946781733409605, "min": 0.078398619717215, "max": 11.990447444220385, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 10.656310680205934, "min": 0.7055875774549349, "max": 247.520980425179, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 82.87572337962963, "min": 19.81304868062337, "max": 141.02953423394098, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 2237.64453125, "min": 440.5219039916992, "max": 2280.235191345215, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 44.38486165056626, "min": 10.05215057068401, "max": 69.64021114508311, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 1198.391264565289, "min": 240.03722366690636, "max": 1198.391264565289, "count": 100 }, "Agent.Environment.LessonNumber.difficulty.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "Agent.Environment.LessonNumber.difficulty.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "Agent.Environment.LessonNumber.task.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "Agent.Environment.LessonNumber.task.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "Agent.Environment.EpisodeLength.mean": { "value": 204.66666666666666, "min": 93.75, "max": 497.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 5526.0, "min": 1719.0, "max": 6831.0, "count": 100 }, "Agent.Step.mean": { "value": 449812.0, "min": 4398.0, "max": 449812.0, "count": 100 }, "Agent.Step.sum": { "value": 449812.0, "min": 4398.0, "max": 449812.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.006913419347256422, "min": -0.0063050780445337296, "max": 0.12888027727603912, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.145181804895401, "min": -0.1460437923669815, "max": 3.479767322540283, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 42.51063919067383, "min": 1.8513860702514648, "max": 50.33930206298828, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 892.7234497070312, "min": 46.28465270996094, "max": 1408.047119140625, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 228.74893406459265, "min": 46.219611057421055, "max": 290.4283050537109, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 4803.727615356445, "min": 1038.7959022521973, "max": 4803.727615356445, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.013974522018716448, "min": 0.011297034891322255, "max": 0.18975708599794994, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.2934649623930454, "min": 0.22433854267001152, "max": 4.174655891954899, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 228.74893406459265, "min": 46.219611057421055, "max": 290.4283050537109, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 4803.727615356445, "min": 1038.7959022521973, "max": 4803.727615356445, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.07224695668662981, "min": 0.055277328552870916, "max": 0.08372609338543394, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14449391337325962, "min": 0.055277328552870916, "max": 0.15900131116321137, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 225.9630463348935, "min": 5.860518129248368, "max": 225.9630463348935, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 451.926092669787, "min": 5.860518129248368, "max": 451.926092669787, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.7790994069999974e-06, "min": 1.7790994069999974e-06, "max": 0.00029834400055199994, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 3.5581988139999947e-06, "min": 3.5581988139999947e-06, "max": 0.0005912520029159999, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.100593, "min": 0.100593, "max": 0.19944800000000004, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.201186, "min": 0.10142999999999998, "max": 0.3970840000000001, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 6.924069999999992e-05, "min": 6.924069999999992e-05, "max": 0.009944855199999998, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00013848139999999984, "min": 0.00013848139999999984, "max": 0.019708691599999995, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0028177442157939587, "min": 0.0024900277077004014, "max": 0.3886077385722545, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.0056354884315879174, "min": 0.0024900277077004014, "max": 0.3886077385722545, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.9829481481387896, "min": 3.857355904957605, "max": 4.39014532691554, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.965896296277579, "min": 3.857355904957605, "max": 8.717200434508444, "count": 99 }, "Agent.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Agent.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716671234", "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\pdsie\\anaconda3\\envs\\mlagents20\\Scripts\\mlagents-learn c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/configs/mlagents/tmp/train/WildfireResourceManagement_difficulty_8_task_0_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_8_task_0_run_id_0_train --base-port 5006", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.7.1+cu110", "numpy_version": "1.21.0", "end_time_seconds": "1716673111" }, "total": 1877.4795203, "count": 1, "self": 0.2012331000003087, "children": { "run_training.setup": { "total": 0.057823100000000016, "count": 1, "self": 0.057823100000000016 }, "TrainerController.start_learning": { "total": 1877.2204640999998, "count": 1, "self": 1.2166694000222833, "children": { "TrainerController._reset_env": { "total": 2.1442506999999997, "count": 1, "self": 2.1442506999999997 }, "TrainerController.advance": { "total": 1873.7536908999778, "count": 50157, "self": 1.0207458000056704, "children": { "env_step": { "total": 1872.732945099972, "count": 50157, "self": 1584.8345274999333, "children": { "SubprocessEnvManager._take_step": { "total": 287.39775570001245, "count": 50157, "self": 1.9877286999894181, "children": { "TorchPolicy.evaluate": { "total": 285.41002700002304, "count": 50157, "self": 285.41002700002304 } } }, "workers": { "total": 0.5006619000262265, "count": 50157, "self": 0.0, "children": { "worker_root": { "total": 1874.5358007000282, "count": 50157, "is_parallel": true, "self": 352.3841908000252, "children": { "steps_from_proto": { "total": 0.000249600000000072, "count": 1, "is_parallel": true, "self": 0.00011890000000014389, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001306999999999281, "count": 2, "is_parallel": true, "self": 0.0001306999999999281 } } }, "UnityEnvironment.step": { "total": 1522.151360300003, "count": 50157, "is_parallel": true, "self": 3.7453855999726784, "children": { "UnityEnvironment._generate_step_input": { "total": 4.608074200023985, "count": 50157, "is_parallel": true, "self": 4.608074200023985 }, "communicator.exchange": { "total": 1503.4560867999946, "count": 50157, "is_parallel": true, "self": 1503.4560867999946 }, "steps_from_proto": { "total": 10.34181370001179, "count": 50157, "is_parallel": true, "self": 5.356283000016858, "children": { "_process_rank_one_or_two_observation": { "total": 4.985530699994931, "count": 100314, "is_parallel": true, "self": 4.985530699994931 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.2599999965677853e-05, "count": 1, "self": 2.2599999965677853e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1873.6321939000304, "count": 93646, "is_parallel": true, "self": 3.4664417000290086, "children": { "process_trajectory": { "total": 1485.2527727000006, "count": 93646, "is_parallel": true, "self": 1485.2527727000006 }, "_update_policy": { "total": 384.9129795000009, "count": 148, "is_parallel": true, "self": 188.9460652999935, "children": { "TorchPPOOptimizer.update": { "total": 195.9669142000074, "count": 10284, "is_parallel": true, "self": 195.9669142000074 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1058304999999109, "count": 1, "self": 0.014507299999877432, "children": { "RLTrainer._checkpoint": { "total": 0.09132320000003347, "count": 1, "self": 0.09132320000003347 } } } } } } }