{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.840954303741455, "min": 3.824573040008545, "max": 4.376417636871338, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 20913.99609375, "min": 8704.244140625, "max": 32441.447265625, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8844443354341719, "min": 0.6462963503543977, "max": 0.8999998793005943, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 39.799995094537735, "min": 7.299999713897705, "max": 61.39999267458916, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 44.65506867253118, "min": 5.183370861742231, "max": 204.7496075100369, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 2009.4780902639031, "min": 279.9020265340805, "max": 3452.556253552437, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.2664910261799399, "min": 0.1047856067177943, "max": 10.791231377671162, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 11.992096178097295, "min": 2.3146310513839126, "max": 299.0446553565562, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 32.170304446750215, "min": 14.268592225180733, "max": 150.80484178331164, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1447.6637001037598, "min": 443.10023975372314, "max": 2396.3430638313293, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 16.353615532673622, "min": 7.39306378364563, "max": 80.06239223480225, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 735.9126989703129, "min": 194.66514086723328, "max": 1118.2563444972038, "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": 0.0020331591367721558, "min": -0.01999807544052601, "max": 0.11944062262773514, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.08539268374443054, "min": -0.9399095177650452, "max": 4.180421829223633, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 40.62111282348633, "min": 0.2851587235927582, "max": 45.50162887573242, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 1706.086669921875, "min": 11.691507339477539, "max": 2222.79443359375, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 52.5391713096982, "min": 17.885152323032493, "max": 361.33335172213043, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 2206.645195007324, "min": 968.859085559845, "max": 4737.388134002686, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.006350158051299374, "min": 0.005583618249712062, "max": 0.18180645166373835, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.26670663815457374, "min": 0.1619249292416498, "max": 7.454064518213272, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 52.5391713096982, "min": 17.885152323032493, "max": 361.33335172213043, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 2206.645195007324, "min": 968.859085559845, "max": 4737.388134002686, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.063536120154438, "min": 0.05455417974271636, "max": 0.07857325897849579, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.127072240308876, "min": 0.05455417974271636, "max": 0.20946030842661412, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 104.72049866689343, "min": 0.962940000825458, "max": 255.13963254292807, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 209.44099733378687, "min": 0.962940000825458, "max": 391.84998753865557, "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": 0.002479477593393257, "min": 0.001664362004136338, "max": 0.37563059092671786, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.004958955186786514, "min": 0.0018040557356832165, "max": 0.37563059092671786, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.85361607520901, "min": 3.781625284868128, "max": 4.390431465925993, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.70723215041802, "min": 3.781625284868128, "max": 12.324647450573229, "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": "1716633990", "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_0_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_1_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": "1716635594" }, "total": 1604.2192071, "count": 1, "self": 0.2187648999999965, "children": { "run_training.setup": { "total": 0.05890530000000005, "count": 1, "self": 0.05890530000000005 }, "TrainerController.start_learning": { "total": 1603.9415368999998, "count": 1, "self": 1.1650278999932198, "children": { "TrainerController._reset_env": { "total": 2.0822798999999996, "count": 1, "self": 2.0822798999999996 }, "TrainerController.advance": { "total": 1600.6075365000065, "count": 50201, "self": 1.0454456000204573, "children": { "env_step": { "total": 1599.562090899986, "count": 50201, "self": 1321.5207513999762, "children": { "SubprocessEnvManager._take_step": { "total": 277.5657273999984, "count": 50201, "self": 1.8167531000220833, "children": { "TorchPolicy.evaluate": { "total": 275.74897429997634, "count": 50201, "self": 275.74897429997634 } } }, "workers": { "total": 0.47561210001138976, "count": 50201, "self": 0.0, "children": { "worker_root": { "total": 1601.3577724999916, "count": 50201, "is_parallel": true, "self": 343.3875831000139, "children": { "steps_from_proto": { "total": 0.00026009999999998534, "count": 1, "is_parallel": true, "self": 0.00011960000000010851, "children": { "_process_rank_one_or_two_observation": { "total": 0.00014049999999987683, "count": 2, "is_parallel": true, "self": 0.00014049999999987683 } } }, "UnityEnvironment.step": { "total": 1257.9699292999776, "count": 50201, "is_parallel": true, "self": 3.6019024999789053, "children": { "UnityEnvironment._generate_step_input": { "total": 4.785271999992973, "count": 50201, "is_parallel": true, "self": 4.785271999992973 }, "communicator.exchange": { "total": 1239.082793400009, "count": 50201, "is_parallel": true, "self": 1239.082793400009 }, "steps_from_proto": { "total": 10.499961399996645, "count": 50201, "is_parallel": true, "self": 5.412605099983018, "children": { "_process_rank_one_or_two_observation": { "total": 5.087356300013626, "count": 100402, "is_parallel": true, "self": 5.087356300013626 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.220000010311196e-05, "count": 1, "self": 2.220000010311196e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1600.8696196000012, "count": 76131, "is_parallel": true, "self": 2.347892499994032, "children": { "process_trajectory": { "total": 1216.8828683000079, "count": 76131, "is_parallel": true, "self": 1216.8828683000079 }, "_update_policy": { "total": 381.63885879999924, "count": 150, "is_parallel": true, "self": 188.25779600000348, "children": { "TorchPPOOptimizer.update": { "total": 193.38106279999576, "count": 10314, "is_parallel": true, "self": 193.38106279999576 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0866704000000027, "count": 1, "self": 0.005369399999835878, "children": { "RLTrainer._checkpoint": { "total": 0.08130100000016682, "count": 1, "self": 0.08130100000016682 } } } } } } }