{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.8786609172821045, "min": 3.686828851699829, "max": 4.382565498352051, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 19059.740234375, "min": 6006.9013671875, "max": 32376.2578125, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8592591600285636, "min": 0.5694444589316845, "max": 0.8999998362527953, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 23.199997320771217, "min": 7.299999222159386, "max": 39.499996066093445, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 676.3128243552314, "min": 17.499365912543404, "max": 2073.9751586914062, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 18260.446257591248, "min": 157.49429321289062, "max": 35529.07872009277, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.12663081612575938, "min": 0.027889348294896383, "max": 5.256550948652956, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 3.419032035395503, "min": 0.25100413465406746, "max": 104.89926034212112, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 47.111211423520686, "min": 8.807972378200954, "max": 124.24823760986328, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1272.0027084350586, "min": 79.2717514038086, "max": 2347.0828351974487, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 23.820514658534968, "min": 3.3417732649379306, "max": 71.48251779874165, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 643.1538957804441, "min": 30.075959384441376, "max": 1215.9338610172272, "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": 181.66666666666666, "min": 96.33333333333333, "max": 473.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 4905.0, "min": 1512.0, "max": 7803.0, "count": 100 }, "Agent.Step.mean": { "value": 449977.0, "min": 4405.0, "max": 449977.0, "count": 100 }, "Agent.Step.sum": { "value": 449977.0, "min": 4405.0, "max": 449977.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": -0.0027963249012827873, "min": -0.0640050545334816, "max": 0.08479417115449905, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": -0.055926498025655746, "min": -1.9373459815979004, "max": 1.9520596265792847, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 280.9388122558594, "min": 4.700740814208984, "max": 431.2846984863281, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 5618.7763671875, "min": 122.2192611694336, "max": 10420.7529296875, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 795.0527629852295, "min": 175.3416471848121, "max": 2244.743329729353, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 15901.05525970459, "min": 4558.882826805115, "max": 33298.71598815918, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.009948330989573151, "min": 0.00850029930472374, "max": 0.28112685100899804, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.19896661979146302, "min": 0.1912378901615739, "max": 5.18032369017601, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 795.0527629852295, "min": 175.3416471848121, "max": 2244.743329729353, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 15901.05525970459, "min": 4558.882826805115, "max": 33298.71598815918, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.07050905195391158, "min": 0.05391141423886573, "max": 0.09056872081961118, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14101810390782316, "min": 0.05391141423886573, "max": 0.15813102597509238, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 8408.508837266401, "min": 144.39980033591942, "max": 18611.196139865453, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 16817.017674532803, "min": 144.39980033591942, "max": 24134.184972426472, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.4610995129999955e-06, "min": 1.4610995129999955e-06, "max": 0.00029848200050600006, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 2.922199025999991e-06, "min": 2.922199025999991e-06, "max": 0.0005858280047239997, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10048699999999999, "min": 0.10048699999999999, "max": 0.199494, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20097399999999999, "min": 0.101576, "max": 0.3952760000000001, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 5.865129999999986e-05, "min": 5.865129999999986e-05, "max": 0.009949450600000001, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00011730259999999973, "min": 0.00011730259999999973, "max": 0.0195280724, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.001982385548134599, "min": 0.001982385548134599, "max": 0.4862046896242628, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.003964771096269198, "min": 0.0020015653682917004, "max": 0.4862046896242628, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.8768466524779797, "min": 3.6591388005726984, "max": 4.390673973981072, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.753693304955959, "min": 3.77407243847847, "max": 8.708318433307465, "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": "1716701865", "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_3_task_2_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_3_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": "1716703577" }, "total": 1711.8388165, "count": 1, "self": 0.19528070000001208, "children": { "run_training.setup": { "total": 0.054822100000000096, "count": 1, "self": 0.054822100000000096 }, "TrainerController.start_learning": { "total": 1711.5887137, "count": 1, "self": 1.1612224999903447, "children": { "TrainerController._reset_env": { "total": 2.08878, "count": 1, "self": 2.08878 }, "TrainerController.advance": { "total": 1708.2559128000096, "count": 50074, "self": 1.0293657999998231, "children": { "env_step": { "total": 1707.2265470000098, "count": 50074, "self": 1432.3362323000447, "children": { "SubprocessEnvManager._take_step": { "total": 274.4136104999957, "count": 50074, "self": 1.763352100004056, "children": { "TorchPolicy.evaluate": { "total": 272.6502583999916, "count": 50074, "self": 272.6502583999916 } } }, "workers": { "total": 0.4767041999693711, "count": 50074, "self": 0.0, "children": { "worker_root": { "total": 1709.076763599999, "count": 50074, "is_parallel": true, "self": 335.70913500000916, "children": { "steps_from_proto": { "total": 0.00025209999999997734, "count": 1, "is_parallel": true, "self": 0.00012210000000001386, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012999999999996348, "count": 2, "is_parallel": true, "self": 0.00012999999999996348 } } }, "UnityEnvironment.step": { "total": 1373.3673764999899, "count": 50074, "is_parallel": true, "self": 3.315785500001539, "children": { "UnityEnvironment._generate_step_input": { "total": 4.013429599998185, "count": 50074, "is_parallel": true, "self": 4.013429599998185 }, "communicator.exchange": { "total": 1356.3925525000009, "count": 50074, "is_parallel": true, "self": 1356.3925525000009 }, "steps_from_proto": { "total": 9.64560889998912, "count": 50074, "is_parallel": true, "self": 4.986471899987435, "children": { "_process_rank_one_or_two_observation": { "total": 4.659137000001686, "count": 100148, "is_parallel": true, "self": 4.659137000001686 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.3300000066228677e-05, "count": 1, "self": 2.3300000066228677e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1708.3414885000182, "count": 84964, "is_parallel": true, "self": 2.678123999962736, "children": { "process_trajectory": { "total": 1349.691457900058, "count": 84964, "is_parallel": true, "self": 1349.691457900058 }, "_update_policy": { "total": 355.9719065999975, "count": 141, "is_parallel": true, "self": 173.82212770000345, "children": { "TorchPPOOptimizer.update": { "total": 182.14977889999406, "count": 10335, "is_parallel": true, "self": 182.14977889999406 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08277509999993526, "count": 1, "self": 0.004725999999891428, "children": { "RLTrainer._checkpoint": { "total": 0.07804910000004384, "count": 1, "self": 0.07804910000004384 } } } } } } }