{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.9548728466033936, "min": 3.7825467586517334, "max": 4.389046669006348, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 19683.40234375, "min": 4316.8203125, "max": 30010.265625, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8666665683741923, "min": 0.5916667206005918, "max": 0.8999998172124227, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 23.39999734610319, "min": 6.699999988079071, "max": 30.899997159838676, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 108.60578582904957, "min": 9.206332196791967, "max": 341.07094319661456, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 2932.3562173843384, "min": 110.20612096786499, "max": 4579.761431694031, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 2.1966807070421055, "min": 0.621840530489054, "max": 25.95005997021993, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 59.31037909013685, "min": 6.678540506865829, "max": 371.12828171253204, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 55.544664241649485, "min": 17.002084299370093, "max": 214.19122314453125, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1499.7059345245361, "min": 204.6931972503662, "max": 2993.9510498046875, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 37.2182973380442, "min": 8.3942994011773, "max": 99.9260475370619, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 1004.8940281271935, "min": 106.93240201473236, "max": 1616.2819256782532, "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": -0.004506892990320921, "min": -0.012754673138260841, "max": 0.14270028471946716, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": -0.09915164858102798, "min": -0.28825098276138306, "max": 3.2247281074523926, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 46.51727294921875, "min": 1.7920188903808594, "max": 52.542354583740234, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 1023.3800048828125, "min": 46.592491149902344, "max": 1576.2706298828125, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 145.4518632888794, "min": 47.06385822296143, "max": 415.89921951293945, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 3199.9409923553467, "min": 1321.8755187988281, "max": 5734.89436340332, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.01323541139506481, "min": 0.010237292789567549, "max": 0.2343111080319985, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.2911790506914258, "min": 0.18846597848460078, "max": 5.389155484735966, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 145.4518632888794, "min": 47.06385822296143, "max": 415.89921951293945, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 3199.9409923553467, "min": 1321.8755187988281, "max": 5734.89436340332, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06451408900884968, "min": 0.05516614062556376, "max": 0.0802689345609569, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.12902817801769936, "min": 0.05516614062556376, "max": 0.1605378691219138, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 125.26563884479143, "min": 11.501119662022244, "max": 246.85574188232422, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 250.53127768958285, "min": 11.501119662022244, "max": 452.8039452446832, "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": 0.002727612785897238, "min": 0.0017549071719216976, "max": 0.37060696955608285, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.005455225571794476, "min": 0.0017549071719216976, "max": 0.37060696955608285, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.9357052565395056, "min": 3.7637806651236, "max": 4.391513147215912, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.871410513079011, "min": 3.7637806651236, "max": 8.755219182424378, "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": "1716703578", "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_0_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_4_task_0_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": "1716705325" }, "total": 1747.2495218, "count": 1, "self": 0.3092979999998988, "children": { "run_training.setup": { "total": 0.05243310000000001, "count": 1, "self": 0.05243310000000001 }, "TrainerController.start_learning": { "total": 1746.8877907, "count": 1, "self": 1.1912608999941767, "children": { "TrainerController._reset_env": { "total": 2.1261732, "count": 1, "self": 2.1261732 }, "TrainerController.advance": { "total": 1743.477684600006, "count": 50210, "self": 1.0407735000096636, "children": { "env_step": { "total": 1742.4369110999962, "count": 50210, "self": 1466.3057363000175, "children": { "SubprocessEnvManager._take_step": { "total": 275.6518068999717, "count": 50210, "self": 1.757567699972185, "children": { "TorchPolicy.evaluate": { "total": 273.8942391999995, "count": 50210, "self": 273.8942391999995 } } }, "workers": { "total": 0.4793679000068716, "count": 50210, "self": 0.0, "children": { "worker_root": { "total": 1744.1928242000038, "count": 50210, "is_parallel": true, "self": 336.9768800999925, "children": { "steps_from_proto": { "total": 0.0002489999999999437, "count": 1, "is_parallel": true, "self": 0.00011439999999995898, "children": { "_process_rank_one_or_two_observation": { "total": 0.00013459999999998473, "count": 2, "is_parallel": true, "self": 0.00013459999999998473 } } }, "UnityEnvironment.step": { "total": 1407.2156951000113, "count": 50210, "is_parallel": true, "self": 3.365289799987977, "children": { "UnityEnvironment._generate_step_input": { "total": 4.068777900013746, "count": 50210, "is_parallel": true, "self": 4.068777900013746 }, "communicator.exchange": { "total": 1390.1194222000072, "count": 50210, "is_parallel": true, "self": 1390.1194222000072 }, "steps_from_proto": { "total": 9.662205200002209, "count": 50210, "is_parallel": true, "self": 4.984321300001236, "children": { "_process_rank_one_or_two_observation": { "total": 4.677883900000973, "count": 100420, "is_parallel": true, "self": 4.677883900000973 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.199999994445534e-05, "count": 1, "self": 2.199999994445534e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1743.5692256000063, "count": 87305, "is_parallel": true, "self": 2.906663100038486, "children": { "process_trajectory": { "total": 1386.3971686999687, "count": 87305, "is_parallel": true, "self": 1386.3971686999687 }, "_update_policy": { "total": 354.2653937999993, "count": 148, "is_parallel": true, "self": 173.25306739999456, "children": { "TorchPPOOptimizer.update": { "total": 181.01232640000472, "count": 10317, "is_parallel": true, "self": 181.01232640000472 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09265000000004875, "count": 1, "self": 0.0049618000000464235, "children": { "RLTrainer._checkpoint": { "total": 0.08768820000000233, "count": 1, "self": 0.08768820000000233 } } } } } } }