{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.9072349071502686, "min": 3.896219253540039, "max": 4.385494709014893, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 32492.56640625, "min": 3738.46923828125, "max": 32492.56640625, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8833332214918401, "min": 0.6022222694423464, "max": 0.8999998817841212, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 31.799995973706245, "min": 7.3999984562397, "max": 40.099994622170925, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 721.4021077917682, "min": 80.86749778323703, "max": 2428.178514268663, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 25970.475880503654, "min": 2353.4279419481754, "max": 43707.21325683594, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.3633727075903658, "min": 0.18966750469472674, "max": 6.678156415207519, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 13.081417473253168, "min": 1.7070075422525406, "max": 169.08945786952972, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 53.49935699833764, "min": 22.186935265858967, "max": 157.86320326063367, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1925.976851940155, "min": 270.33209228515625, "max": 2356.889991760254, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 28.4905375193982, "min": 9.365763707293404, "max": 78.2373907632298, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 1025.6593506983352, "min": 119.87503230571747, "max": 1408.2730337381363, "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": 230.5, "min": 89.6, "max": 499.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 8298.0, "min": 936.0, "max": 8298.0, "count": 100 }, "Agent.Step.mean": { "value": 449883.0, "min": 4251.0, "max": 449883.0, "count": 100 }, "Agent.Step.sum": { "value": 449883.0, "min": 4251.0, "max": 449883.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.000553550198674202, "min": -0.06830383092164993, "max": 0.12467946857213974, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.016052955761551857, "min": -1.5709881782531738, "max": 4.416498184204102, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 300.3558044433594, "min": 1.9085078239440918, "max": 309.19232177734375, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 8710.318359375, "min": 62.98075866699219, "max": 11249.7255859375, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 723.2452566048195, "min": 122.79987020203562, "max": 2623.8573888142905, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 20974.112441539764, "min": 4052.3957166671753, "max": 32908.48686981201, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.01017263026281806, "min": 0.008879438338156503, "max": 0.17959920384667136, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.2950062776217237, "min": 0.17983429972082376, "max": 3.7317505534738302, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 723.2452566048195, "min": 122.79987020203562, "max": 2623.8573888142905, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 20974.112441539764, "min": 4052.3957166671753, "max": 32908.48686981201, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06636851126569565, "min": 0.053887202596617126, "max": 0.08192256537056866, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.1327370225313913, "min": 0.053887202596617126, "max": 0.16384513074113732, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 12299.918729428893, "min": 191.80274963378906, "max": 15915.296110026042, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 24599.837458857786, "min": 191.80274963378906, "max": 24599.837458857786, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.827099390999995e-06, "min": 1.827099390999995e-06, "max": 0.00029819400060199984, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 3.65419878199999e-06, "min": 3.65419878199999e-06, "max": 0.0005916540027819999, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.100609, "min": 0.100609, "max": 0.19939800000000005, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.201218, "min": 0.10158800000000001, "max": 0.39721799999999996, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 7.083909999999983e-05, "min": 7.083909999999983e-05, "max": 0.009939860200000004, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00014167819999999967, "min": 0.00014167819999999967, "max": 0.0197220782, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0023117968791026484, "min": 0.001999419695628738, "max": 0.3829007114446352, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.004623593758205297, "min": 0.001999419695628738, "max": 0.3829007114446352, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.9139821650805295, "min": 3.8770363981073555, "max": 4.3893865706428645, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.827964330161059, "min": 3.8770363981073555, "max": 8.711278208050347, "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": "1716696791", "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_2_task_2_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_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": "1716698424" }, "total": 1633.0382524, "count": 1, "self": 0.20053069999994477, "children": { "run_training.setup": { "total": 0.05210500000000007, "count": 1, "self": 0.05210500000000007 }, "TrainerController.start_learning": { "total": 1632.7856167, "count": 1, "self": 1.227762799991524, "children": { "TrainerController._reset_env": { "total": 2.081207, "count": 1, "self": 2.081207 }, "TrainerController.advance": { "total": 1629.3801854000085, "count": 50488, "self": 0.9495130000152585, "children": { "env_step": { "total": 1628.4306723999932, "count": 50488, "self": 1357.1245237999951, "children": { "SubprocessEnvManager._take_step": { "total": 270.8429244000024, "count": 50488, "self": 1.727493900040713, "children": { "TorchPolicy.evaluate": { "total": 269.1154304999617, "count": 50488, "self": 269.1154304999617 } } }, "workers": { "total": 0.463224199995818, "count": 50488, "self": 0.0, "children": { "worker_root": { "total": 1630.2148361, "count": 50488, "is_parallel": true, "self": 330.95029039997416, "children": { "steps_from_proto": { "total": 0.0002427000000000401, "count": 1, "is_parallel": true, "self": 0.00011300000000002974, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012970000000001036, "count": 2, "is_parallel": true, "self": 0.00012970000000001036 } } }, "UnityEnvironment.step": { "total": 1299.2643030000258, "count": 50488, "is_parallel": true, "self": 3.3135401000449747, "children": { "UnityEnvironment._generate_step_input": { "total": 4.033551899959847, "count": 50488, "is_parallel": true, "self": 4.033551899959847 }, "communicator.exchange": { "total": 1282.423853400033, "count": 50488, "is_parallel": true, "self": 1282.423853400033 }, "steps_from_proto": { "total": 9.493357599988132, "count": 50488, "is_parallel": true, "self": 4.8367685000013, "children": { "_process_rank_one_or_two_observation": { "total": 4.656589099986832, "count": 100976, "is_parallel": true, "self": 4.656589099986832 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.2299999955066596e-05, "count": 1, "self": 2.2299999955066596e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1629.6933504000099, "count": 80299, "is_parallel": true, "self": 2.4942578999898615, "children": { "process_trajectory": { "total": 1277.753238200021, "count": 80299, "is_parallel": true, "self": 1277.753238200021 }, "_update_policy": { "total": 349.4458542999988, "count": 147, "is_parallel": true, "self": 170.815070199999, "children": { "TorchPPOOptimizer.update": { "total": 178.6307840999998, "count": 10305, "is_parallel": true, "self": 178.6307840999998 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09643920000007711, "count": 1, "self": 0.004752600000074381, "children": { "RLTrainer._checkpoint": { "total": 0.09168660000000273, "count": 1, "self": 0.09168660000000273 } } } } } } }