{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 4.148153781890869, "min": 3.9534835815429688, "max": 4.3843994140625, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 14448.01953125, "min": 4130.9931640625, "max": 36413.6484375, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8444442889756627, "min": 0.5472222614205546, "max": 0.89999994525203, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 15.199997201561928, "min": 6.7999992072582245, "max": 39.49999599903822, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 45.45161990324656, "min": 8.356466677143342, "max": 285.98129738701715, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 818.1291582584381, "min": 120.73436641693115, "max": 2573.8316764831543, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 6.296157315787342, "min": 0.44460721862398916, "max": 18.87570232856605, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 113.33083168417215, "min": 8.002929935231805, "max": 311.1089367866516, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 39.144233809577095, "min": 15.426498691240946, "max": 175.01845126681857, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 704.5962085723877, "min": 277.67697644233704, "max": 2443.025146484375, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 20.77334968911277, "min": 7.703126282327705, "max": 97.11700802379184, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 373.92029440402985, "min": 138.6562730818987, "max": 1160.4680968523026, "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": 192.5, "min": 77.5, "max": 424.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 3465.0, "min": 972.0, "max": 8451.0, "count": 100 }, "Agent.Step.mean": { "value": 449921.0, "min": 4257.0, "max": 449921.0, "count": 100 }, "Agent.Step.sum": { "value": 449921.0, "min": 4257.0, "max": 449921.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.006086220033466816, "min": -0.030397245660424232, "max": 0.11500242352485657, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.12172439694404602, "min": -0.7678675055503845, "max": 2.5300533771514893, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 35.00136947631836, "min": 0.45898157358169556, "max": 45.52016067504883, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 700.0274047851562, "min": 9.638612747192383, "max": 1422.7843017578125, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 116.78929290771484, "min": 34.70127656724718, "max": 263.7130589204676, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 2335.785858154297, "min": 624.6229782104492, "max": 4483.122001647949, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.026885639876127243, "min": 0.011392961287955668, "max": 0.19850951331582936, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.5377127975225449, "min": 0.3170678894966841, "max": 4.367209292948246, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 116.78929290771484, "min": 34.70127656724718, "max": 263.7130589204676, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 2335.785858154297, "min": 624.6229782104492, "max": 4483.122001647949, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.07446588068177887, "min": 0.054723067815260346, "max": 0.08446220237140854, "count": 100 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.07446588068177887, "min": 0.05769777173797289, "max": 0.15926789021261079, "count": 100 }, "Agent.Losses.ValueLoss.mean": { "value": 56.94056144415163, "min": 5.67844514357738, "max": 132.7524534570603, "count": 100 }, "Agent.Losses.ValueLoss.sum": { "value": 56.94056144415163, "min": 5.67844514357738, "max": 265.5049069141206, "count": 100 }, "Agent.Policy.LearningRate.mean": { "value": 3.30099889999997e-07, "min": 3.30099889999997e-07, "max": 0.000297708000764, "count": 100 }, "Agent.Policy.LearningRate.sum": { "value": 3.30099889999997e-07, "min": 3.30099889999997e-07, "max": 0.0005794560068479999, "count": 100 }, "Agent.Policy.Epsilon.mean": { "value": 0.10011000000000005, "min": 0.10011000000000005, "max": 0.19923600000000005, "count": 100 }, "Agent.Policy.Epsilon.sum": { "value": 0.10011000000000005, "min": 0.10011000000000005, "max": 0.39315200000000006, "count": 100 }, "Agent.Policy.Beta.mean": { "value": 2.09889999999999e-05, "min": 2.09889999999999e-05, "max": 0.009923676400000001, "count": 100 }, "Agent.Policy.Beta.sum": { "value": 2.09889999999999e-05, "min": 2.09889999999999e-05, "max": 0.019315884799999995, "count": 100 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.004819725028367019, "min": 0.0031541522863941887, "max": 0.35365391216981107, "count": 100 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.004819725028367019, "min": 0.0031541522863941887, "max": 0.35365391216981107, "count": 100 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 4.031139305993622, "min": 3.9234148219779685, "max": 4.3919764787722855, "count": 100 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 4.031139305993622, "min": 3.9234148219779685, "max": 8.701281236848612, "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": "1716676997", "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_9_task_0_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_9_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": "1716678930" }, "total": 1933.2950784, "count": 1, "self": 0.20031569999991916, "children": { "run_training.setup": { "total": 0.04912669999999997, "count": 1, "self": 0.04912669999999997 }, "TrainerController.start_learning": { "total": 1933.045636, "count": 1, "self": 1.1320330000128251, "children": { "TrainerController._reset_env": { "total": 2.0998837, "count": 1, "self": 2.0998837 }, "TrainerController.advance": { "total": 1929.7127992999872, "count": 50051, "self": 1.0170403999695736, "children": { "env_step": { "total": 1928.6957589000176, "count": 50051, "self": 1614.5856488000143, "children": { "SubprocessEnvManager._take_step": { "total": 313.61869270002325, "count": 50051, "self": 2.0127296000302977, "children": { "TorchPolicy.evaluate": { "total": 311.60596309999295, "count": 50051, "self": 311.60596309999295 } } }, "workers": { "total": 0.4914173999801288, "count": 50051, "self": 0.0, "children": { "worker_root": { "total": 1930.3753732999985, "count": 50051, "is_parallel": true, "self": 381.07223699998553, "children": { "steps_from_proto": { "total": 0.00026689999999995884, "count": 1, "is_parallel": true, "self": 0.0001217999999998387, "children": { "_process_rank_one_or_two_observation": { "total": 0.00014510000000012013, "count": 2, "is_parallel": true, "self": 0.00014510000000012013 } } }, "UnityEnvironment.step": { "total": 1549.302869400013, "count": 50051, "is_parallel": true, "self": 4.033853899988571, "children": { "UnityEnvironment._generate_step_input": { "total": 5.385735700026307, "count": 50051, "is_parallel": true, "self": 5.385735700026307 }, "communicator.exchange": { "total": 1528.606026799997, "count": 50051, "is_parallel": true, "self": 1528.606026799997 }, "steps_from_proto": { "total": 11.277253000001165, "count": 50051, "is_parallel": true, "self": 5.8760223999817764, "children": { "_process_rank_one_or_two_observation": { "total": 5.401230600019389, "count": 100102, "is_parallel": true, "self": 5.401230600019389 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.119999999194988e-05, "count": 1, "self": 2.119999999194988e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1929.6505315000145, "count": 94826, "is_parallel": true, "self": 3.2473841000171433, "children": { "process_trajectory": { "total": 1508.196806199998, "count": 94826, "is_parallel": true, "self": 1508.196806199998 }, "_update_policy": { "total": 418.20634119999926, "count": 143, "is_parallel": true, "self": 204.59906950000686, "children": { "TorchPPOOptimizer.update": { "total": 213.6072716999924, "count": 10347, "is_parallel": true, "self": 213.6072716999924 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10089880000009543, "count": 1, "self": 0.0072571000000607455, "children": { "RLTrainer._checkpoint": { "total": 0.09364170000003469, "count": 1, "self": 0.09364170000003469 } } } } } } }