{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.9017300605773926, "min": 3.8140387535095215, "max": 4.3714494705200195, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 21244.919921875, "min": 8572.8515625, "max": 32024.3671875, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8933332022693422, "min": 0.6500000520436852, "max": 0.8999998793005943, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 40.1999941021204, "min": 7.4999992325901985, "max": 62.59999257326126, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 455.88364140722484, "min": 53.61029998461405, "max": 2424.1639472113716, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 20514.76386332512, "min": 2894.956199169159, "max": 41510.122690439224, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.30548179356548943, "min": 0.05765622271535954, "max": 4.903017125965562, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 13.746680710447023, "min": 1.0378120088764717, "max": 110.67634117603302, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 31.89151145087348, "min": 14.07080864906311, "max": 141.05380249023438, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1435.1180152893066, "min": 498.6379585266113, "max": 2363.7911472320557, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 16.32038382192239, "min": 7.486613300111559, "max": 88.22554196251764, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 734.4172719865076, "min": 224.51533195376396, "max": 1192.3509817123413, "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": 120.2, "min": 65.16666666666667, "max": 436.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 5409.0, "min": 2052.0, "max": 7722.0, "count": 100 }, "Agent.Step.mean": { "value": 449904.0, "min": 4441.0, "max": 449904.0, "count": 100 }, "Agent.Step.sum": { "value": 449904.0, "min": 4441.0, "max": 449904.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": -0.009130329824984074, "min": -0.08197839558124542, "max": 0.1488860845565796, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": -0.38347384333610535, "min": -2.705286979675293, "max": 5.070252895355225, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 267.82708740234375, "min": 0.8720908761024475, "max": 337.3840637207031, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 11248.7373046875, "min": 35.7557258605957, "max": 14407.11328125, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 302.4706774666196, "min": 76.75898319337426, "max": 2716.065643310547, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 12703.768453598022, "min": 3147.1183109283447, "max": 35308.85336303711, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.006048896419261361, "min": 0.005580994091799547, "max": 0.18199072705536354, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.25405364960897714, "min": 0.16184882866218686, "max": 7.461619809269905, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 302.4706774666196, "min": 76.75898319337426, "max": 2716.065643310547, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 12703.768453598022, "min": 3147.1183109283447, "max": 35308.85336303711, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06425880937903025, "min": 0.05538995831233004, "max": 0.0795730839303711, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.1285176187580605, "min": 0.05538995831233004, "max": 0.2090949601998242, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 5232.771832818718, "min": 9.863332196518227, "max": 21489.855577256945, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 10465.543665637437, "min": 9.863332196518227, "max": 29943.240201822915, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.6080994640000096e-06, "min": 1.6080994640000096e-06, "max": 0.00029842200052599994, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 3.216198928000019e-06, "min": 3.216198928000019e-06, "max": 0.0005854140048619999, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10053600000000001, "min": 0.10053600000000001, "max": 0.19947400000000004, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20107200000000003, "min": 0.101584, "max": 0.490534, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 6.354640000000032e-05, "min": 6.354640000000032e-05, "max": 0.009947452599999998, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00012709280000000063, "min": 0.00012709280000000063, "max": 0.0195142862, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0025058726663171734, "min": 0.0014629171960804537, "max": 0.37563059092671786, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.005011745332634347, "min": 0.001611489856396943, "max": 0.37563059092671786, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.8885767201156565, "min": 3.79713204795239, "max": 4.390431465925993, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.777153440231313, "min": 3.79713204795239, "max": 12.45364493658303, "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": "1716691861", "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_1_task_2_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_1_task_2_run_id_1_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": "1716693456" }, "total": 1595.0740624, "count": 1, "self": 0.1920430000000124, "children": { "run_training.setup": { "total": 0.05646689999999999, "count": 1, "self": 0.05646689999999999 }, "TrainerController.start_learning": { "total": 1594.8255525, "count": 1, "self": 1.1509333000137758, "children": { "TrainerController._reset_env": { "total": 2.0875927, "count": 1, "self": 2.0875927 }, "TrainerController.advance": { "total": 1591.484710599986, "count": 50201, "self": 1.0372009999775855, "children": { "env_step": { "total": 1590.4475096000085, "count": 50201, "self": 1316.8220555999865, "children": { "SubprocessEnvManager._take_step": { "total": 273.16257040000954, "count": 50201, "self": 1.735983200026169, "children": { "TorchPolicy.evaluate": { "total": 271.4265871999834, "count": 50201, "self": 271.4265871999834 } } }, "workers": { "total": 0.4628836000123995, "count": 50201, "self": 0.0, "children": { "worker_root": { "total": 1592.2150314999903, "count": 50201, "is_parallel": true, "self": 333.5507993999897, "children": { "steps_from_proto": { "total": 0.0002470999999999446, "count": 1, "is_parallel": true, "self": 0.00012069999999986258, "children": { "_process_rank_one_or_two_observation": { "total": 0.000126400000000082, "count": 2, "is_parallel": true, "self": 0.000126400000000082 } } }, "UnityEnvironment.step": { "total": 1258.6639850000006, "count": 50201, "is_parallel": true, "self": 3.258150600005365, "children": { "UnityEnvironment._generate_step_input": { "total": 4.005038999999481, "count": 50201, "is_parallel": true, "self": 4.005038999999481 }, "communicator.exchange": { "total": 1242.0187904000136, "count": 50201, "is_parallel": true, "self": 1242.0187904000136 }, "steps_from_proto": { "total": 9.382004999982113, "count": 50201, "is_parallel": true, "self": 4.845075099989843, "children": { "_process_rank_one_or_two_observation": { "total": 4.536929899992271, "count": 100402, "is_parallel": true, "self": 4.536929899992271 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.8299999939918052e-05, "count": 1, "self": 2.8299999939918052e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1591.7403541000006, "count": 76587, "is_parallel": true, "self": 2.4294420000276205, "children": { "process_trajectory": { "total": 1220.6428112999731, "count": 76587, "is_parallel": true, "self": 1220.6428112999731 }, "_update_policy": { "total": 368.6681007999998, "count": 150, "is_parallel": true, "self": 179.46155949999405, "children": { "TorchPPOOptimizer.update": { "total": 189.20654130000577, "count": 10314, "is_parallel": true, "self": 189.20654130000577 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10228760000018156, "count": 1, "self": 0.014001800000187359, "children": { "RLTrainer._checkpoint": { "total": 0.0882857999999942, "count": 1, "self": 0.0882857999999942 } } } } } } }