{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.959440231323242, "min": 3.946554660797119, "max": 4.384186744689941, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 18458.91015625, "min": 8798.0322265625, "max": 30735.79296875, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8888888185222944, "min": 0.6370370828167156, "max": 0.8999999091029167, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 23.999998100101948, "min": 6.69999922066927, "max": 34.40000247210264, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 41.60684348918773, "min": 9.279088221214435, "max": 174.12117195129395, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 1123.3847742080688, "min": 189.5553515702486, "max": 3645.4411582946777, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.22388378598815994, "min": 0.18191154123309794, "max": 27.389015058676403, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 6.044862221680319, "min": 3.2744077421957627, "max": 246.50113552808762, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 36.97786811546043, "min": 21.879398345947266, "max": 200.36048889160156, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 998.4024391174316, "min": 445.91785049438477, "max": 2111.0100593566895, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 16.880418524422026, "min": 11.25219029629672, "max": 88.87926024860806, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 455.77130015939474, "min": 192.76574563980103, "max": 1223.8117544111196, "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": 171.33333333333334, "min": 112.2, "max": 485.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 4626.0, "min": 2142.0, "max": 7497.0, "count": 100 }, "Agent.Step.mean": { "value": 449953.0, "min": 4410.0, "max": 449953.0, "count": 100 }, "Agent.Step.sum": { "value": 449953.0, "min": 4410.0, "max": 449953.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.005593667738139629, "min": -0.00885381456464529, "max": 0.13125886023044586, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.17340369522571564, "min": -0.12395340204238892, "max": 2.5827291011810303, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 39.983795166015625, "min": 2.5574610233306885, "max": 50.32978820800781, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 1239.4976806640625, "min": 99.74098205566406, "max": 1459.6314697265625, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 68.22372793382213, "min": 39.648218106000854, "max": 268.4897787911551, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 2114.9355659484863, "min": 789.2640495300293, "max": 4499.848472595215, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.009430301706156424, "min": 0.008391974103038333, "max": 0.20418489040722224, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.2923393528908491, "min": 0.24254547525197268, "max": 7.948641270399094, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 68.22372793382213, "min": 39.648218106000854, "max": 268.4897787911551, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 2114.9355659484863, "min": 789.2640495300293, "max": 4499.848472595215, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06390889440835626, "min": 0.05888922307672652, "max": 0.0824222353879701, "count": 100 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.06390889440835626, "min": 0.059122073790058495, "max": 0.15948358503647775, "count": 100 }, "Agent.Losses.ValueLoss.mean": { "value": 98.11443244086371, "min": 8.328265375305232, "max": 191.94933087898022, "count": 100 }, "Agent.Losses.ValueLoss.sum": { "value": 98.11443244086371, "min": 9.668982664744059, "max": 311.18359328761244, "count": 100 }, "Agent.Policy.LearningRate.mean": { "value": 1.4520995159999864e-06, "min": 1.4520995159999864e-06, "max": 0.000298578000474, "count": 100 }, "Agent.Policy.LearningRate.sum": { "value": 1.4520995159999864e-06, "min": 1.4520995159999864e-06, "max": 0.000590892003036, "count": 100 }, "Agent.Policy.Epsilon.mean": { "value": 0.10048399999999998, "min": 0.10048399999999998, "max": 0.199526, "count": 100 }, "Agent.Policy.Epsilon.sum": { "value": 0.10048399999999998, "min": 0.10048399999999998, "max": 0.396964, "count": 100 }, "Agent.Policy.Beta.mean": { "value": 5.835159999999957e-05, "min": 5.835159999999957e-05, "max": 0.0099526474, "count": 100 }, "Agent.Policy.Beta.sum": { "value": 5.835159999999957e-05, "min": 5.835159999999957e-05, "max": 0.019696703600000004, "count": 100 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.003257173762432541, "min": 0.0022394847018447415, "max": 0.5244236296663681, "count": 100 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.003257173762432541, "min": 0.0025311765472266685, "max": 0.5244236296663681, "count": 100 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.927374499815482, "min": 3.927374499815482, "max": 4.390662242968877, "count": 100 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 3.927374499815482, "min": 3.927374499815482, "max": 8.75307583079438, "count": 100 }, "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": "1716659977", "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_6_task_0_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_6_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": "1716661808" }, "total": 1830.3791383999999, "count": 1, "self": 0.1947284000000309, "children": { "run_training.setup": { "total": 0.05258930000000006, "count": 1, "self": 0.05258930000000006 }, "TrainerController.start_learning": { "total": 1830.1318207, "count": 1, "self": 1.1137619999894923, "children": { "TrainerController._reset_env": { "total": 3.6721985999999998, "count": 1, "self": 3.6721985999999998 }, "TrainerController.advance": { "total": 1825.2504619000104, "count": 50104, "self": 0.9997688000048583, "children": { "env_step": { "total": 1824.2506931000055, "count": 50104, "self": 1548.8022804000075, "children": { "SubprocessEnvManager._take_step": { "total": 274.95246520000546, "count": 50104, "self": 1.7765231000274753, "children": { "TorchPolicy.evaluate": { "total": 273.175942099978, "count": 50104, "self": 273.175942099978 } } }, "workers": { "total": 0.4959474999925533, "count": 50104, "self": 0.0, "children": { "worker_root": { "total": 1825.979588299994, "count": 50104, "is_parallel": true, "self": 336.668187100031, "children": { "steps_from_proto": { "total": 0.0002440999999997473, "count": 1, "is_parallel": true, "self": 0.00011669999999952552, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012740000000022178, "count": 2, "is_parallel": true, "self": 0.00012740000000022178 } } }, "UnityEnvironment.step": { "total": 1489.311157099963, "count": 50104, "is_parallel": true, "self": 3.347504399974241, "children": { "UnityEnvironment._generate_step_input": { "total": 4.025324000007989, "count": 50104, "is_parallel": true, "self": 4.025324000007989 }, "communicator.exchange": { "total": 1472.3087831000075, "count": 50104, "is_parallel": true, "self": 1472.3087831000075 }, "steps_from_proto": { "total": 9.629545599973387, "count": 50104, "is_parallel": true, "self": 4.849076299960905, "children": { "_process_rank_one_or_two_observation": { "total": 4.780469300012482, "count": 100208, "is_parallel": true, "self": 4.780469300012482 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.0599999970727367e-05, "count": 1, "self": 2.0599999970727367e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1825.1567651000066, "count": 92197, "is_parallel": true, "self": 3.151860299970167, "children": { "process_trajectory": { "total": 1463.061188400037, "count": 92197, "is_parallel": true, "self": 1463.061188400037 }, "_update_policy": { "total": 358.9437163999994, "count": 148, "is_parallel": true, "self": 175.86173580000428, "children": { "TorchPPOOptimizer.update": { "total": 183.08198059999512, "count": 10278, "is_parallel": true, "self": 183.08198059999512 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09537760000011986, "count": 1, "self": 0.005526800000325238, "children": { "RLTrainer._checkpoint": { "total": 0.08985079999979462, "count": 1, "self": 0.08985079999979462 } } } } } } }