{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.97270131111145, "min": 3.8580334186553955, "max": 4.385058879852295, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 19772.134765625, "min": 4324.59814453125, "max": 30275.548828125, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8925924670917017, "min": 0.5944444899343782, "max": 0.8999998337692685, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 24.099996611475945, "min": 7.299999460577965, "max": 32.099995002150536, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 1132.227039054588, "min": 112.27245076497395, "max": 3760.4518534342446, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 30570.130054473877, "min": 1010.4520568847656, "max": 46698.55090332031, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.4156373774174682, "min": 0.12152427987328135, "max": 4.414028333293067, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 11.222209190271641, "min": 3.078512976934718, "max": 150.33448672667146, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 56.56567022535536, "min": 18.60294959280226, "max": 203.521976047092, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1527.2730960845947, "min": 187.9657154083252, "max": 2957.372100830078, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 37.497118130878164, "min": 9.254810196382028, "max": 102.94365169604619, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 1012.4221895337105, "min": 95.39323675632477, "max": 1618.2430572509766, "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": 184.0, "min": 87.0, "max": 447.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 4968.0, "min": 1026.0, "max": 7254.0, "count": 100 }, "Agent.Step.mean": { "value": 449820.0, "min": 4428.0, "max": 449820.0, "count": 100 }, "Agent.Step.sum": { "value": 449820.0, "min": 4428.0, "max": 449820.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": -0.00548894889652729, "min": -0.03430468589067459, "max": 0.14062848687171936, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": -0.12075687944889069, "min": -0.9807142615318298, "max": 2.8125698566436768, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 270.135009765625, "min": 6.275667190551758, "max": 340.4035339355469, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 5942.97021484375, "min": 163.16734313964844, "max": 9848.359375, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 1034.0226169932973, "min": 250.50194498697917, "max": 2925.5960973103843, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 22748.49757385254, "min": 5705.194595336914, "max": 39389.590560913086, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.011027288665487007, "min": 0.008789539543123772, "max": 0.2349855530521144, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.24260035064071417, "min": 0.1741041336208582, "max": 5.404667720198631, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 1034.0226169932973, "min": 250.50194498697917, "max": 2925.5960973103843, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 22748.49757385254, "min": 5705.194595336914, "max": 39389.590560913086, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06593079745640486, "min": 0.05476249791940467, "max": 0.07900114618241787, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.13186159491280972, "min": 0.05476249791940467, "max": 0.15389319697316464, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 8362.757220247608, "min": 301.55181486710256, "max": 21009.97041015625, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 16725.514440495215, "min": 301.55181486710256, "max": 30410.252495659723, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.0980996339999984e-06, "min": 1.0980996339999984e-06, "max": 0.00029796000068000006, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 2.1961992679999967e-06, "min": 2.1961992679999967e-06, "max": 0.0005911860029379999, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10036600000000001, "min": 0.10036600000000001, "max": 0.19932, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20073200000000002, "min": 0.10149800000000003, "max": 0.397062, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 4.656339999999997e-05, "min": 4.656339999999997e-05, "max": 0.009932068000000002, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 9.312679999999994e-05, "min": 9.312679999999994e-05, "max": 0.019706493800000002, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0022638690914241577, "min": 0.0015879822761120125, "max": 0.37060696955608285, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.004527738182848315, "min": 0.0015879822761120125, "max": 0.37060696955608285, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.9615057295277003, "min": 3.838027181047382, "max": 4.391513147215912, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.923011459055401, "min": 3.838027181047382, "max": 8.72829988494254, "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": "1716652710", "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_4_task_2_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_4_task_2_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": "1716654492" }, "total": 1782.0044866, "count": 1, "self": 0.20458140000005187, "children": { "run_training.setup": { "total": 0.05663320000000005, "count": 1, "self": 0.05663320000000005 }, "TrainerController.start_learning": { "total": 1781.743272, "count": 1, "self": 1.1691789000110475, "children": { "TrainerController._reset_env": { "total": 2.115984, "count": 1, "self": 2.115984 }, "TrainerController.advance": { "total": 1778.3634315999889, "count": 50210, "self": 1.0052072999892516, "children": { "env_step": { "total": 1777.3582242999996, "count": 50210, "self": 1501.7532938000159, "children": { "SubprocessEnvManager._take_step": { "total": 275.113631199983, "count": 50210, "self": 1.7641998000028138, "children": { "TorchPolicy.evaluate": { "total": 273.3494313999802, "count": 50210, "self": 273.3494313999802 } } }, "workers": { "total": 0.49129930000063515, "count": 50210, "self": 0.0, "children": { "worker_root": { "total": 1779.1295885000159, "count": 50210, "is_parallel": true, "self": 335.8695537000117, "children": { "steps_from_proto": { "total": 0.00024120000000005248, "count": 1, "is_parallel": true, "self": 0.00011600000000000499, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001252000000000475, "count": 2, "is_parallel": true, "self": 0.0001252000000000475 } } }, "UnityEnvironment.step": { "total": 1443.2597936000043, "count": 50210, "is_parallel": true, "self": 3.2992694999989, "children": { "UnityEnvironment._generate_step_input": { "total": 4.078019399997862, "count": 50210, "is_parallel": true, "self": 4.078019399997862 }, "communicator.exchange": { "total": 1426.4108941000034, "count": 50210, "is_parallel": true, "self": 1426.4108941000034 }, "steps_from_proto": { "total": 9.47161060000408, "count": 50210, "is_parallel": true, "self": 4.886855700005743, "children": { "_process_rank_one_or_two_observation": { "total": 4.584754899998337, "count": 100420, "is_parallel": true, "self": 4.584754899998337 } } } } } } } } } } } } }, "trainer_threads": { "total": 1.9400000155656016e-05, "count": 1, "self": 1.9400000155656016e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1778.4394830000017, "count": 89000, "is_parallel": true, "self": 2.936941700023681, "children": { "process_trajectory": { "total": 1411.5376232999786, "count": 89000, "is_parallel": true, "self": 1411.5376232999786 }, "_update_policy": { "total": 363.96491799999944, "count": 148, "is_parallel": true, "self": 178.18578389999726, "children": { "TorchPPOOptimizer.update": { "total": 185.77913410000218, "count": 10317, "is_parallel": true, "self": 185.77913410000218 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09465809999983321, "count": 1, "self": 0.005292699999927208, "children": { "RLTrainer._checkpoint": { "total": 0.089365399999906, "count": 1, "self": 0.089365399999906 } } } } } } }