{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.9181978702545166, "min": 3.8353826999664307, "max": 4.385557174682617, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 21651.9609375, "min": 7004.57666015625, "max": 27602.22265625, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8666667496716535, "min": 0.5777778308838606, "max": 0.9000000953674316, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 23.400002241134644, "min": 7.700000762939453, "max": 32.20000338554382, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 2.152441685018992, "min": 0.8010983359482553, "max": 15.489594587573299, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 58.11592549551278, "min": 11.439244419336319, "max": 418.21905386447906, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 304.5739384757148, "min": 26.05030299226443, "max": 468.1476593017578, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 8223.4963388443, "min": 937.8109077215195, "max": 8394.559112548828, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 64.0783942187274, "min": 20.735190947850544, "max": 117.72799767388238, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1730.1166439056396, "min": 435.9099578857422, "max": 1998.507007598877, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 35.4022040632036, "min": 11.265056636598375, "max": 57.77317428588867, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 955.8595097064972, "min": 220.9379529953003, "max": 1043.3600313663483, "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": 204.66666666666666, "min": 93.75, "max": 497.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 5526.0, "min": 1719.0, "max": 6831.0, "count": 100 }, "Agent.Step.mean": { "value": 449812.0, "min": 4398.0, "max": 449812.0, "count": 100 }, "Agent.Step.sum": { "value": 449812.0, "min": 4398.0, "max": 449812.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.0032545796129852533, "min": -0.04245872423052788, "max": 0.11642169952392578, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.06834617257118225, "min": -0.9340919256210327, "max": 3.118682861328125, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 101.64611053466797, "min": 3.4324796199798584, "max": 117.11848449707031, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 2134.568359375, "min": 85.8119888305664, "max": 3188.197509765625, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 388.0023089817592, "min": 76.50909111022949, "max": 603.0836317274305, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 8148.048488616943, "min": 1912.7272777557373, "max": 8148.048488616943, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.027668442399728866, "min": 0.02111277556805699, "max": 0.18603225509551438, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.5810372903943062, "min": 0.5008933562785387, "max": 4.0927096121013165, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 388.0023089817592, "min": 76.50909111022949, "max": 603.0836317274305, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 8148.048488616943, "min": 1912.7272777557373, "max": 8148.048488616943, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.07081948476148817, "min": 0.051579486404856045, "max": 0.08544279739522097, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14163896952297633, "min": 0.051579486404856045, "max": 0.15435190841607335, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 919.6023082684374, "min": 36.81519386224579, "max": 919.6023082684374, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 1839.2046165368747, "min": 36.81519386224579, "max": 1839.2046165368747, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.7790994069999974e-06, "min": 1.7790994069999974e-06, "max": 0.00029834400055199994, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 3.5581988139999947e-06, "min": 3.5581988139999947e-06, "max": 0.0005912520029159999, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.100593, "min": 0.100593, "max": 0.19944800000000004, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.201186, "min": 0.10142999999999998, "max": 0.3970840000000001, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 6.924069999999992e-05, "min": 6.924069999999992e-05, "max": 0.009944855199999998, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00013848139999999984, "min": 0.00013848139999999984, "max": 0.019708691599999995, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.005482690535463514, "min": 0.004134121945955687, "max": 0.3886077385722545, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.010965381070927028, "min": 0.004134121945955687, "max": 0.3886077385722545, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.85200771986676, "min": 3.732027288467165, "max": 4.39014532691554, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.70401543973352, "min": 3.732027288467165, "max": 8.739337876731273, "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": "1716727898", "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_8_task_1_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_8_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": "1716729806" }, "total": 1907.8616203000001, "count": 1, "self": 0.2091005000002042, "children": { "run_training.setup": { "total": 0.05204299999999995, "count": 1, "self": 0.05204299999999995 }, "TrainerController.start_learning": { "total": 1907.6004768, "count": 1, "self": 1.3724266000042462, "children": { "TrainerController._reset_env": { "total": 2.2182755, "count": 1, "self": 2.2182755 }, "TrainerController.advance": { "total": 1903.8876972999958, "count": 50157, "self": 1.1044949999766231, "children": { "env_step": { "total": 1902.7832023000192, "count": 50157, "self": 1589.0755829000168, "children": { "SubprocessEnvManager._take_step": { "total": 313.19396319999316, "count": 50157, "self": 2.029523899969149, "children": { "TorchPolicy.evaluate": { "total": 311.164439300024, "count": 50157, "self": 311.164439300024 } } }, "workers": { "total": 0.5136562000090978, "count": 50157, "self": 0.0, "children": { "worker_root": { "total": 1904.7780526000035, "count": 50157, "is_parallel": true, "self": 385.78522210001825, "children": { "steps_from_proto": { "total": 0.0002884999999999138, "count": 1, "is_parallel": true, "self": 0.00012699999999998823, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001614999999999256, "count": 2, "is_parallel": true, "self": 0.0001614999999999256 } } }, "UnityEnvironment.step": { "total": 1518.9925419999854, "count": 50157, "is_parallel": true, "self": 4.3082015999791565, "children": { "UnityEnvironment._generate_step_input": { "total": 5.646964899999924, "count": 50157, "is_parallel": true, "self": 5.646964899999924 }, "communicator.exchange": { "total": 1497.4812175999834, "count": 50157, "is_parallel": true, "self": 1497.4812175999834 }, "steps_from_proto": { "total": 11.556157900023079, "count": 50157, "is_parallel": true, "self": 6.010886400029484, "children": { "_process_rank_one_or_two_observation": { "total": 5.545271499993595, "count": 100314, "is_parallel": true, "self": 5.545271499993595 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.7199999976801337e-05, "count": 1, "self": 2.7199999976801337e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1904.0746734999818, "count": 92880, "is_parallel": true, "self": 3.372148499981222, "children": { "process_trajectory": { "total": 1474.4498105000011, "count": 92880, "is_parallel": true, "self": 1474.4498105000011 }, "_update_policy": { "total": 426.25271449999946, "count": 148, "is_parallel": true, "self": 209.94881250000054, "children": { "TorchPPOOptimizer.update": { "total": 216.3039019999989, "count": 10284, "is_parallel": true, "self": 216.3039019999989 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12205020000010336, "count": 1, "self": 0.005611200000203098, "children": { "RLTrainer._checkpoint": { "total": 0.11643899999990026, "count": 1, "self": 0.11643899999990026 } } } } } } }