{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.773111581802368, "min": 3.609867811203003, "max": 4.382511138916016, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 31343.23828125, "min": 3680.79345703125, "max": 31343.23828125, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8888889816072252, "min": 0.5955556015173594, "max": 0.9000000953674316, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 32.00000333786011, "min": 7.400000661611557, "max": 40.00000434368849, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 1.0236329838323097, "min": 0.39147261530160904, "max": 13.06465654902988, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 36.85078741796315, "min": 7.046507075428963, "max": 281.3741154074669, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 226.40432628658084, "min": 52.50743840535482, "max": 564.7666176689995, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 8150.55574631691, "min": 820.2791519165039, "max": 9137.845397949219, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 54.668125761879814, "min": 21.098224964406754, "max": 131.6296149359809, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1968.0525274276733, "min": 241.36893272399902, "max": 2233.3657302856445, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 26.228197210364872, "min": 9.368682894441816, "max": 69.78266217973497, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 944.2150995731354, "min": 107.97553443908691, "max": 1114.3494420051575, "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": 230.5, "min": 89.6, "max": 499.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 8298.0, "min": 936.0, "max": 8298.0, "count": 100 }, "Agent.Step.mean": { "value": 449883.0, "min": 4251.0, "max": 449883.0, "count": 100 }, "Agent.Step.sum": { "value": 449883.0, "min": 4251.0, "max": 449883.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.013316089287400246, "min": -0.006160436663776636, "max": 0.10405787825584412, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.38616660237312317, "min": -0.12986703217029572, "max": 2.639519214630127, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 103.84432220458984, "min": 1.508461356163025, "max": 111.68872833251953, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 3011.4853515625, "min": 49.77922439575195, "max": 4052.524169921875, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 212.38566474256845, "min": 87.37553246815999, "max": 576.8127671877543, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 6159.184277534485, "min": 2883.39257144928, "max": 8546.511407852173, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.02052150433883071, "min": 0.016388132236897945, "max": 0.1508480669422583, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.5951236258260906, "min": 0.4603901170194149, "max": 3.6766746076755226, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 212.38566474256845, "min": 87.37553246815999, "max": 576.8127671877543, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 6159.184277534485, "min": 2883.39257144928, "max": 8546.511407852173, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.05697476157608132, "min": 0.05697476157608132, "max": 0.08195726283722454, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.11394952315216264, "min": 0.05725877036920924, "max": 0.15617152375893462, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 752.2826052065249, "min": 120.16638068547324, "max": 1094.9797980414496, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 1504.5652104130497, "min": 120.16638068547324, "max": 2106.0909014872027, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.827099390999995e-06, "min": 1.827099390999995e-06, "max": 0.00029819400060199984, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 3.65419878199999e-06, "min": 3.65419878199999e-06, "max": 0.0005916540027819999, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.100609, "min": 0.100609, "max": 0.19939800000000005, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.201218, "min": 0.10158800000000001, "max": 0.39721799999999996, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 7.083909999999983e-05, "min": 7.083909999999983e-05, "max": 0.009939860200000004, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00014167819999999967, "min": 0.00014167819999999967, "max": 0.0197220782, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.005709888912625266, "min": 0.004941627686281526, "max": 0.3829007114446352, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.011419777825250532, "min": 0.004941627686281526, "max": 0.3829007114446352, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.7203084186271385, "min": 3.5755480453644917, "max": 4.3893865706428645, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.440616837254277, "min": 3.5779103217301547, "max": 8.708217721701132, "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": "1716695117", "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_2_task_1_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_task_1_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": "1716696790" }, "total": 1673.0916116, "count": 1, "self": 0.19354520000001685, "children": { "run_training.setup": { "total": 0.05442399999999992, "count": 1, "self": 0.05442399999999992 }, "TrainerController.start_learning": { "total": 1672.8436424000001, "count": 1, "self": 1.2215291000088655, "children": { "TrainerController._reset_env": { "total": 2.0150763, "count": 1, "self": 2.0150763 }, "TrainerController.advance": { "total": 1669.5150304999916, "count": 50488, "self": 0.9888500999973076, "children": { "env_step": { "total": 1668.5261803999942, "count": 50488, "self": 1394.444734999982, "children": { "SubprocessEnvManager._take_step": { "total": 273.61061450000153, "count": 50488, "self": 1.8085848000006877, "children": { "TorchPolicy.evaluate": { "total": 271.80202970000084, "count": 50488, "self": 271.80202970000084 } } }, "workers": { "total": 0.4708309000106299, "count": 50488, "self": 0.0, "children": { "worker_root": { "total": 1670.26575100001, "count": 50488, "is_parallel": true, "self": 334.05342460003885, "children": { "steps_from_proto": { "total": 0.0002727000000000146, "count": 1, "is_parallel": true, "self": 0.00012149999999988559, "children": { "_process_rank_one_or_two_observation": { "total": 0.000151200000000129, "count": 2, "is_parallel": true, "self": 0.000151200000000129 } } }, "UnityEnvironment.step": { "total": 1336.212053699971, "count": 50488, "is_parallel": true, "self": 3.268314199975748, "children": { "UnityEnvironment._generate_step_input": { "total": 4.139222200013775, "count": 50488, "is_parallel": true, "self": 4.139222200013775 }, "communicator.exchange": { "total": 1319.327986900004, "count": 50488, "is_parallel": true, "self": 1319.327986900004 }, "steps_from_proto": { "total": 9.4765303999774, "count": 50488, "is_parallel": true, "self": 4.904830799999759, "children": { "_process_rank_one_or_two_observation": { "total": 4.5716995999776415, "count": 100976, "is_parallel": true, "self": 4.5716995999776415 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.239999980702123e-05, "count": 1, "self": 2.239999980702123e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1669.7951487000128, "count": 82031, "is_parallel": true, "self": 2.6207553000283497, "children": { "process_trajectory": { "total": 1303.9013004999845, "count": 82031, "is_parallel": true, "self": 1303.9013004999845 }, "_update_policy": { "total": 363.2730929, "count": 147, "is_parallel": true, "self": 177.13689009999786, "children": { "TorchPPOOptimizer.update": { "total": 186.13620280000214, "count": 10305, "is_parallel": true, "self": 186.13620280000214 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09198409999999058, "count": 1, "self": 0.005571200000076715, "children": { "RLTrainer._checkpoint": { "total": 0.08641289999991386, "count": 1, "self": 0.08641289999991386 } } } } } } }