{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.9662578105926514, "min": 3.8902809619903564, "max": 4.3802947998046875, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 19525.88671875, "min": 3942.199951171875, "max": 31338.61328125, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8888887448443307, "min": 0.5500000417232513, "max": 0.8999999136560493, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 15.999997407197952, "min": 7.5, "max": 32.299995206296444, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 1026.1174051894081, "min": 1.2436208843460514, "max": 2813.268530951606, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 18470.113293409348, "min": 11.192587959114462, "max": 36061.0396194458, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 0.2600799028037323, "min": 0.013587533599800534, "max": 4.705731664680773, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 4.681438250467181, "min": 0.1222878023982048, "max": 84.7031699642539, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 57.71533436245389, "min": 0.2929872473080953, "max": 174.170406765408, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1038.87601852417, "min": 2.6368852257728577, "max": 2244.8185958862305, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 35.585473120212555, "min": 0.10056810929543442, "max": 78.23635286755032, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 640.538516163826, "min": 0.9051129836589098, "max": 1107.8064243793488, "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": -0.0028904082719236612, "min": -0.0634576678276062, "max": 0.12072662264108658, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": -0.04624653235077858, "min": -1.269153356552124, "max": 3.13889217376709, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 246.62399291992188, "min": 6.235428333282471, "max": 357.42041015625, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 3945.98388671875, "min": 162.1211395263672, "max": 11794.8740234375, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 930.314374923706, "min": 193.45669285456339, "max": 2241.3963661193848, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 14885.029998779297, "min": 5150.876541137695, "max": 35862.341857910156, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.015021562692709267, "min": 0.009544561451841746, "max": 0.22255233503304994, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.24034500308334827, "min": 0.19084811629727483, "max": 5.786360710859299, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 930.314374923706, "min": 193.45669285456339, "max": 2241.3963661193848, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 14885.029998779297, "min": 5150.876541137695, "max": 35862.341857910156, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.0636149788009529, "min": 0.05675364297533792, "max": 0.08363459916303359, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.1272299576019058, "min": 0.05675364297533792, "max": 0.16726919832606718, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 3978.190133520818, "min": 274.94069978560526, "max": 13049.90203814956, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 7956.380267041636, "min": 274.94069978560526, "max": 26099.80407629912, "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": 0.002147874424402681, "min": 0.002037737639971398, "max": 0.38484019738814185, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.004295748848805362, "min": 0.002037737639971398, "max": 0.38484019738814185, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.9688596760422605, "min": 3.8964975935842854, "max": 4.389180887313116, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.937719352084521, "min": 3.911028209659788, "max": 8.685674510777943, "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": "1716768588", "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_2_run_id_2_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_5_task_2_run_id_2_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": "1716770535" }, "total": 1947.7930261, "count": 1, "self": 0.2078475000000708, "children": { "run_training.setup": { "total": 0.05632779999999993, "count": 1, "self": 0.05632779999999993 }, "TrainerController.start_learning": { "total": 1947.5288507999999, "count": 1, "self": 1.0826197000017146, "children": { "TrainerController._reset_env": { "total": 2.3188974, "count": 1, "self": 2.3188974 }, "TrainerController.advance": { "total": 1944.0281442999983, "count": 50091, "self": 0.9824415999921712, "children": { "env_step": { "total": 1943.0457027000061, "count": 50091, "self": 1532.7661559999997, "children": { "SubprocessEnvManager._take_step": { "total": 409.83407730001545, "count": 50091, "self": 1.8083528000054798, "children": { "TorchPolicy.evaluate": { "total": 408.02572450000997, "count": 50091, "self": 408.02572450000997 } } }, "workers": { "total": 0.4454693999908712, "count": 50091, "self": 0.0, "children": { "worker_root": { "total": 1944.6120570000066, "count": 50091, "is_parallel": true, "self": 472.48266330000774, "children": { "steps_from_proto": { "total": 0.0002790999999999766, "count": 1, "is_parallel": true, "self": 0.0001265000000001404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001525999999998362, "count": 2, "is_parallel": true, "self": 0.0001525999999998362 } } }, "UnityEnvironment.step": { "total": 1472.129114599999, "count": 50091, "is_parallel": true, "self": 3.5904693000172756, "children": { "UnityEnvironment._generate_step_input": { "total": 4.666798800006584, "count": 50091, "is_parallel": true, "self": 4.666798800006584 }, "communicator.exchange": { "total": 1454.0078471999661, "count": 50091, "is_parallel": true, "self": 1454.0078471999661 }, "steps_from_proto": { "total": 9.863999300009022, "count": 50091, "is_parallel": true, "self": 5.160215900029229, "children": { "_process_rank_one_or_two_observation": { "total": 4.703783399979793, "count": 100182, "is_parallel": true, "self": 4.703783399979793 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.189999986512703e-05, "count": 1, "self": 2.189999986512703e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1944.1581723999896, "count": 89380, "is_parallel": true, "self": 2.8366435999580517, "children": { "process_trajectory": { "total": 1417.463181500031, "count": 89380, "is_parallel": true, "self": 1417.463181500031 }, "_update_policy": { "total": 523.8583473000007, "count": 143, "is_parallel": true, "self": 254.35360870000864, "children": { "TorchPPOOptimizer.update": { "total": 269.50473859999204, "count": 10296, "is_parallel": true, "self": 269.50473859999204 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09916750000002139, "count": 1, "self": 0.014539000000013402, "children": { "RLTrainer._checkpoint": { "total": 0.08462850000000799, "count": 1, "self": 0.08462850000000799 } } } } } } }