{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.9790024757385254, "min": 3.9426229000091553, "max": 4.384097576141357, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 19588.62890625, "min": 3697.3173828125, "max": 31503.28515625, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8833332272867361, "min": 0.5555555903249316, "max": 0.8999998913043075, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 15.899998091161251, "min": 7.000000223517418, "max": 31.999995470046997, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 80.60973479681545, "min": 0.10768404721360032, "max": 248.34259457058377, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 1450.975226342678, "min": 0.969156424922403, "max": 2945.7017974853516, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.3801335415078534, "min": 0.01641160911983914, "max": 9.644429033001265, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 6.842403747141361, "min": 0.14770448207855225, "max": 219.80404091626406, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 67.59286774529352, "min": 0.2759494384129842, "max": 155.0876719156901, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1216.6716194152832, "min": 2.483544945716858, "max": 2201.0021057128906, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 34.56691179010603, "min": 0.0947068203240633, "max": 77.07207973798116, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 622.2044122219086, "min": 0.8523613829165697, "max": 1007.8357060849667, "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": 273.0, "min": 16.0, "max": 455.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 4914.0, "min": 144.0, "max": 7695.0, "count": 100 }, "Agent.Step.mean": { "value": 449877.0, "min": 4381.0, "max": 449877.0, "count": 100 }, "Agent.Step.sum": { "value": 449877.0, "min": 4381.0, "max": 449877.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.006750881671905518, "min": -0.012739883735775948, "max": 0.11897391825914383, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.10801410675048828, "min": -0.20383813977241516, "max": 3.0933218002319336, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 35.70020294189453, "min": 1.470633864402771, "max": 50.8341064453125, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 571.2032470703125, "min": 38.236480712890625, "max": 1677.5255126953125, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 131.3084635734558, "min": 37.73844643739554, "max": 282.3111138343811, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 2100.935417175293, "min": 1036.8795852661133, "max": 4516.977821350098, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.020240316458512098, "min": 0.011927072860060199, "max": 0.22122024615796712, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.32384506333619356, "min": 0.256887782830745, "max": 5.751726400107145, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 131.3084635734558, "min": 37.73844643739554, "max": 282.3111138343811, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 2100.935417175293, "min": 1036.8795852661133, "max": 4516.977821350098, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06362482790065016, "min": 0.056942009002618164, "max": 0.08438466520563356, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.12724965580130032, "min": 0.056942009002618164, "max": 0.16876933041126713, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 63.23698472603792, "min": 5.822606236139933, "max": 156.46512782007738, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 126.47396945207583, "min": 5.822606236139933, "max": 312.93025564015477, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.8030993989999881e-06, "min": 1.8030993989999881e-06, "max": 0.00029819400060199984, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 3.6061987979999762e-06, "min": 3.6061987979999762e-06, "max": 0.0005861940046020002, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10060100000000004, "min": 0.10060100000000004, "max": 0.19939800000000005, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20120200000000008, "min": 0.10181000000000004, "max": 0.3953980000000001, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 7.003989999999961e-05, "min": 7.003989999999961e-05, "max": 0.009939860200000004, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00014007979999999923, "min": 0.00014007979999999923, "max": 0.019540260200000006, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0028334709095681233, "min": 0.002552407628103493, "max": 0.38484019738814185, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.005666941819136247, "min": 0.002716009190086933, "max": 0.38484019738814185, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.954002788223013, "min": 3.93007966429715, "max": 4.389180887313116, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.908005576446026, "min": 3.9468957362351595, "max": 8.731818569084954, "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": "1716654493", "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_5_task_0_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_5_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": "1716656322" }, "total": 1829.2482914, "count": 1, "self": 0.19380449999994198, "children": { "run_training.setup": { "total": 0.06638769999999994, "count": 1, "self": 0.06638769999999994 }, "TrainerController.start_learning": { "total": 1828.9880992, "count": 1, "self": 1.1153832999816586, "children": { "TrainerController._reset_env": { "total": 2.1201426, "count": 1, "self": 2.1201426 }, "TrainerController.advance": { "total": 1825.6590711000185, "count": 50091, "self": 1.064749900024708, "children": { "env_step": { "total": 1824.5943211999938, "count": 50091, "self": 1548.5461036000024, "children": { "SubprocessEnvManager._take_step": { "total": 275.5569933000056, "count": 50091, "self": 1.7498843000246325, "children": { "TorchPolicy.evaluate": { "total": 273.807108999981, "count": 50091, "self": 273.807108999981 } } }, "workers": { "total": 0.4912242999856691, "count": 50091, "self": 0.0, "children": { "worker_root": { "total": 1826.4210882000307, "count": 50091, "is_parallel": true, "self": 336.4644268000425, "children": { "steps_from_proto": { "total": 0.00036009999999997433, "count": 1, "is_parallel": true, "self": 0.00016790000000010963, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001921999999998647, "count": 2, "is_parallel": true, "self": 0.0001921999999998647 } } }, "UnityEnvironment.step": { "total": 1489.9563012999881, "count": 50091, "is_parallel": true, "self": 3.4311641999943276, "children": { "UnityEnvironment._generate_step_input": { "total": 4.08801820000469, "count": 50091, "is_parallel": true, "self": 4.08801820000469 }, "communicator.exchange": { "total": 1472.8431573999874, "count": 50091, "is_parallel": true, "self": 1472.8431573999874 }, "steps_from_proto": { "total": 9.593961500001807, "count": 50091, "is_parallel": true, "self": 4.881630800029496, "children": { "_process_rank_one_or_two_observation": { "total": 4.712330699972311, "count": 100182, "is_parallel": true, "self": 4.712330699972311 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.1599999854515772e-05, "count": 1, "self": 2.1599999854515772e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1825.5939962999946, "count": 92098, "is_parallel": true, "self": 3.1223809999869445, "children": { "process_trajectory": { "total": 1460.9177770000076, "count": 92098, "is_parallel": true, "self": 1460.9177770000076 }, "_update_policy": { "total": 361.55383830000005, "count": 143, "is_parallel": true, "self": 177.03219429999865, "children": { "TorchPPOOptimizer.update": { "total": 184.5216440000014, "count": 10296, "is_parallel": true, "self": 184.5216440000014 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09348060000002079, "count": 1, "self": 0.005317500000046493, "children": { "RLTrainer._checkpoint": { "total": 0.08816309999997429, "count": 1, "self": 0.08816309999997429 } } } } } } }