{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.895878553390503, "min": 3.798156976699829, "max": 4.382574558258057, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 10238.369140625, "min": 7896.3681640625, "max": 27760.474609375, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8833331987261772, "min": 0.5583333782851696, "max": 0.8999998627437485, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 15.89999757707119, "min": 7.4999985024333, "max": 31.899994932115078, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 284.595914999644, "min": 153.90408929189047, "max": 2259.0255313449434, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 5122.726469993591, "min": 3879.4105949401855, "max": 26762.316802978516, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.5137351515419222, "min": 0.19555388773894972, "max": 3.4479985090179577, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 9.247232727754598, "min": 1.7599849896505475, "max": 93.17613142356277, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 29.29599274529351, "min": 22.066055244869656, "max": 131.33065456814236, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 527.3278694152832, "min": 388.75328063964844, "max": 1922.4526405334473, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 13.033045665257507, "min": 10.607020768052372, "max": 70.97385215759277, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 234.59482197463512, "min": 222.77447228133678, "max": 937.7676983326674, "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": 144.5, "min": 110.5, "max": 483.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 2601.0, "min": 2034.0, "max": 6606.0, "count": 100 }, "Agent.Step.mean": { "value": 449971.0, "min": 4406.0, "max": 449971.0, "count": 100 }, "Agent.Step.sum": { "value": 449971.0, "min": 4406.0, "max": 449971.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.00179284845944494, "min": -0.06635196506977081, "max": 0.10478061437606812, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.037649817764759064, "min": -1.8168004751205444, "max": 2.759366512298584, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 194.49093627929688, "min": 5.094647407531738, "max": 332.0804138183594, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 4084.309814453125, "min": 96.79830169677734, "max": 8891.16796875, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 413.3823020571754, "min": 195.91140566374125, "max": 1908.735560490535, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 8681.028343200684, "min": 4197.615684509277, "max": 24813.562286376953, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.012001433742365666, "min": 0.009087652286612674, "max": 0.19407686740159988, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.252030108589679, "min": 0.1929760556668043, "max": 3.8815373480319977, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 413.3823020571754, "min": 195.91140566374125, "max": 1908.735560490535, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 8681.028343200684, "min": 4197.615684509277, "max": 24813.562286376953, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06969277160863081, "min": 0.05842876552293698, "max": 0.08153026154599129, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.06969277160863081, "min": 0.05842876552293698, "max": 0.15539867630409615, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 2709.7872526041665, "min": 127.48155826992459, "max": 9677.014474051339, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 2709.7872526041665, "min": 127.48155826992459, "max": 19274.98607490406, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.3200995599999879e-06, "min": 1.3200995599999879e-06, "max": 0.0002979480006839999, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 1.3200995599999879e-06, "min": 1.3200995599999879e-06, "max": 0.0005902860032380002, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10043999999999999, "min": 0.10043999999999999, "max": 0.19931600000000002, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.10043999999999999, "min": 0.10043999999999999, "max": 0.3967619999999999, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 5.395599999999961e-05, "min": 5.395599999999961e-05, "max": 0.009931668400000001, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 5.395599999999961e-05, "min": 5.395599999999961e-05, "max": 0.019676523799999995, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0020138267319028576, "min": 0.001961364351287061, "max": 0.3038852005783055, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.0020138267319028576, "min": 0.001961364351287061, "max": 0.3038852005783055, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.84472420056661, "min": 3.77582754872062, "max": 4.390625682142046, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 3.84472420056661, "min": 3.77582754872062, "max": 8.727684051271469, "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": "1716686800", "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_10_task_2_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_10_task_2_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": "1716688655" }, "total": 1855.1568345, "count": 1, "self": 0.29765720000023066, "children": { "run_training.setup": { "total": 0.05249360000000003, "count": 1, "self": 0.05249360000000003 }, "TrainerController.start_learning": { "total": 1854.8066837, "count": 1, "self": 1.1186227000071085, "children": { "TrainerController._reset_env": { "total": 2.155676, "count": 1, "self": 2.155676 }, "TrainerController.advance": { "total": 1851.4361356999925, "count": 50073, "self": 1.0589420999963295, "children": { "env_step": { "total": 1850.3771935999962, "count": 50073, "self": 1570.0748243000082, "children": { "SubprocessEnvManager._take_step": { "total": 279.815693500001, "count": 50073, "self": 1.758176599992339, "children": { "TorchPolicy.evaluate": { "total": 278.05751690000864, "count": 50073, "self": 278.05751690000864 } } }, "workers": { "total": 0.4866757999869873, "count": 50073, "self": 0.0, "children": { "worker_root": { "total": 1852.2739141999834, "count": 50073, "is_parallel": true, "self": 339.68587449997085, "children": { "steps_from_proto": { "total": 0.00025599999999981193, "count": 1, "is_parallel": true, "self": 0.00012009999999973431, "children": { "_process_rank_one_or_two_observation": { "total": 0.00013590000000007763, "count": 2, "is_parallel": true, "self": 0.00013590000000007763 } } }, "UnityEnvironment.step": { "total": 1512.5877837000126, "count": 50073, "is_parallel": true, "self": 3.266162600016969, "children": { "UnityEnvironment._generate_step_input": { "total": 4.061013599981699, "count": 50073, "is_parallel": true, "self": 4.061013599981699 }, "communicator.exchange": { "total": 1495.6063755999867, "count": 50073, "is_parallel": true, "self": 1495.6063755999867 }, "steps_from_proto": { "total": 9.654231900027323, "count": 50073, "is_parallel": true, "self": 4.931584100038769, "children": { "_process_rank_one_or_two_observation": { "total": 4.722647799988554, "count": 100146, "is_parallel": true, "self": 4.722647799988554 } } } } } } } } } } } } }, "trainer_threads": { "total": 1.9199999996999395e-05, "count": 1, "self": 1.9199999996999395e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1851.3835212999995, "count": 93617, "is_parallel": true, "self": 3.22288490001597, "children": { "process_trajectory": { "total": 1484.4343171999842, "count": 93617, "is_parallel": true, "self": 1484.4343171999842 }, "_update_policy": { "total": 363.72631919999935, "count": 143, "is_parallel": true, "self": 178.05386050000186, "children": { "TorchPPOOptimizer.update": { "total": 185.6724586999975, "count": 10281, "is_parallel": true, "self": 185.6724586999975 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0962301000001844, "count": 1, "self": 0.005531900000278256, "children": { "RLTrainer._checkpoint": { "total": 0.09069819999990614, "count": 1, "self": 0.09069819999990614 } } } } } } }