{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.706364870071411, "min": 3.457319974899292, "max": 4.390174865722656, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 13442.9853515625, "min": 8464.4580078125, "max": 29634.39453125, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8999998470147451, "min": 0.547222251072526, "max": 0.8999998470147451, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 16.19999724626541, "min": 6.699999637901783, "max": 37.89999862015247, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 50.14008625348409, "min": 5.578264324201478, "max": 247.97332196765475, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 902.5215525627136, "min": 179.57133507728577, "max": 4463.519795417786, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.5825647181983461, "min": 0.2835087590953799, "max": 19.160854612787563, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 10.486164927570229, "min": 5.103157663716838, "max": 413.3232282400131, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 33.95084857940674, "min": 22.32279067569309, "max": 132.23717583550348, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 611.1152744293213, "min": 558.7826709747314, "max": 2097.7965507507324, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 17.793587919428116, "min": 11.182480812072754, "max": 68.06744170188904, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 320.2845825497061, "min": 278.04094982147217, "max": 1194.6557540297508, "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": 200.5, "min": 99.6, "max": 454.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 3609.0, "min": 1971.0, "max": 6993.0, "count": 100 }, "Agent.Step.mean": { "value": 449967.0, "min": 4460.0, "max": 449967.0, "count": 100 }, "Agent.Step.sum": { "value": 449967.0, "min": 4460.0, "max": 449967.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.005283562000840902, "min": -0.005888283718377352, "max": 0.07057717442512512, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.08982055634260178, "min": -0.1295422464609146, "max": 2.1032252311706543, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 38.87142562866211, "min": 0.9718481302261353, "max": 62.582191467285156, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 660.814208984375, "min": 24.29620361328125, "max": 1857.610107421875, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 114.8073844909668, "min": 31.032124277949332, "max": 427.8070411682129, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 1951.7255363464355, "min": 1034.7373847961426, "max": 6300.8376388549805, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.019781928619041163, "min": 0.011907589350206157, "max": 0.36124941557645796, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.33629278652369976, "min": 0.2716328580863774, "max": 5.41874123364687, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 114.8073844909668, "min": 31.032124277949332, "max": 427.8070411682129, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 1951.7255363464355, "min": 1034.7373847961426, "max": 6300.8376388549805, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.07060870294601934, "min": 0.05792925613267081, "max": 0.08752357298690899, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14121740589203868, "min": 0.05792925613267081, "max": 0.17033054319277308, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 91.22412368448022, "min": 6.4376300227257515, "max": 260.8982047286688, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 182.44824736896044, "min": 6.4376300227257515, "max": 353.62499101426863, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 8.670997110000013e-07, "min": 8.670997110000013e-07, "max": 0.00029775000075000005, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 1.7341994220000026e-06, "min": 1.7341994220000026e-06, "max": 0.0005801040066320001, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10028899999999999, "min": 0.10028899999999999, "max": 0.19924999999999993, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20057799999999998, "min": 0.10254, "max": 0.39336799999999994, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 3.887110000000003e-05, "min": 3.887110000000003e-05, "max": 0.009925074999999997, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 7.774220000000006e-05, "min": 7.774220000000006e-05, "max": 0.0193374632, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0033502325712044933, "min": 0.00247651579928869, "max": 0.3516008852957151, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.006700465142408987, "min": 0.0029627155814696813, "max": 0.3516008852957151, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.7413376433751586, "min": 3.453024881415897, "max": 4.390753862185356, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.482675286750317, "min": 3.4748421020996876, "max": 8.728238554622816, "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": "1716665494", "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_7_task_0_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_7_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": "1716667365" }, "total": 1871.0884486999998, "count": 1, "self": 0.19610609999995177, "children": { "run_training.setup": { "total": 0.051763800000000026, "count": 1, "self": 0.051763800000000026 }, "TrainerController.start_learning": { "total": 1870.8405788, "count": 1, "self": 1.2469002000177625, "children": { "TrainerController._reset_env": { "total": 2.1159754, "count": 1, "self": 2.1159754 }, "TrainerController.advance": { "total": 1867.3851553999823, "count": 50136, "self": 0.9651854999833631, "children": { "env_step": { "total": 1866.419969899999, "count": 50136, "self": 1593.0787984999856, "children": { "SubprocessEnvManager._take_step": { "total": 272.8701689000018, "count": 50136, "self": 1.7521967000085397, "children": { "TorchPolicy.evaluate": { "total": 271.11797219999323, "count": 50136, "self": 271.11797219999323 } } }, "workers": { "total": 0.4710025000115081, "count": 50136, "self": 0.0, "children": { "worker_root": { "total": 1868.1920430000057, "count": 50136, "is_parallel": true, "self": 332.8805892000207, "children": { "steps_from_proto": { "total": 0.0002461999999998632, "count": 1, "is_parallel": true, "self": 0.00011779999999972368, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012840000000013951, "count": 2, "is_parallel": true, "self": 0.00012840000000013951 } } }, "UnityEnvironment.step": { "total": 1535.311207599985, "count": 50136, "is_parallel": true, "self": 3.4137411999922733, "children": { "UnityEnvironment._generate_step_input": { "total": 4.059499199995798, "count": 50136, "is_parallel": true, "self": 4.059499199995798 }, "communicator.exchange": { "total": 1517.9100985999967, "count": 50136, "is_parallel": true, "self": 1517.9100985999967 }, "steps_from_proto": { "total": 9.927868600000162, "count": 50136, "is_parallel": true, "self": 4.982524799970456, "children": { "_process_rank_one_or_two_observation": { "total": 4.945343800029706, "count": 100272, "is_parallel": true, "self": 4.945343800029706 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.2500000113723218e-05, "count": 1, "self": 2.2500000113723218e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1867.440884499972, "count": 96056, "is_parallel": true, "self": 3.1386700999696586, "children": { "process_trajectory": { "total": 1524.9112227000023, "count": 96056, "is_parallel": true, "self": 1524.9112227000023 }, "_update_policy": { "total": 339.3909917000001, "count": 151, "is_parallel": true, "self": 167.08894660000124, "children": { "TorchPPOOptimizer.update": { "total": 172.30204509999885, "count": 10320, "is_parallel": true, "self": 172.30204509999885 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09252529999980652, "count": 1, "self": 0.005861799999820505, "children": { "RLTrainer._checkpoint": { "total": 0.08666349999998602, "count": 1, "self": 0.08666349999998602 } } } } } } }