{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.915287971496582, "min": 3.8286855220794678, "max": 4.388269424438477, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 14165.51171875, "min": 8352.5712890625, "max": 29077.494140625, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.900000093711747, "min": 0.5527778027786149, "max": 0.9000000953674316, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 16.200001686811447, "min": 7.100000619888306, "max": 38.90000382065773, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 1.427949388175168, "min": 0.8593527575241864, "max": 13.473621871736315, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 25.703088987153023, "min": 20.61485666036606, "max": 331.6421630382538, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 245.42562950981988, "min": 39.79780564043257, "max": 619.4954562717014, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 4417.661331176758, "min": 1432.7210030555725, "max": 7888.533269882202, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 56.38962088690864, "min": 25.348989952935113, "max": 134.0869344075521, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1015.0131759643555, "min": 597.5732574462891, "max": 1808.8400115966797, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 28.600747956169975, "min": 13.09142631954617, "max": 72.36796273125543, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 514.8134632110596, "min": 316.33687686920166, "max": 930.763605594635, "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": 200.5, "min": 99.6, "max": 454.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 3609.0, "min": 1971.0, "max": 6993.0, "count": 100 }, "Agent.Step.mean": { "value": 449967.0, "min": 4460.0, "max": 449967.0, "count": 100 }, "Agent.Step.sum": { "value": 449967.0, "min": 4460.0, "max": 449967.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.007648792117834091, "min": -0.037885017693042755, "max": 0.058897458016872406, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.13002946972846985, "min": -0.7198153138160706, "max": 1.5313339233398438, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 79.99057006835938, "min": 1.986396312713623, "max": 122.08625793457031, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 1359.8397216796875, "min": 49.659908294677734, "max": 3734.32177734375, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 337.52348866182217, "min": 95.12189712524415, "max": 545.2072296142578, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 5737.899307250977, "min": 2378.0474281311035, "max": 9027.143272399902, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.0344109117765637, "min": 0.018234928297859273, "max": 0.3611468697587649, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.5849855002015829, "min": 0.4833681769669056, "max": 5.4172030463814735, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 337.52348866182217, "min": 95.12189712524415, "max": 545.2072296142578, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 5737.899307250977, "min": 2378.0474281311035, "max": 9027.143272399902, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06865449139139485, "min": 0.05436178324486788, "max": 0.088415523402785, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.1373089827827897, "min": 0.058083717240601455, "max": 0.15414777564144722, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 505.428675700849, "min": 69.4129291436611, "max": 979.6034150965073, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 1010.857351401698, "min": 69.4129291436611, "max": 1746.0488988430955, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 8.670997110000013e-07, "min": 8.670997110000013e-07, "max": 0.00029775000075000005, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 1.7341994220000026e-06, "min": 1.7341994220000026e-06, "max": 0.0005801040066320001, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10028899999999999, "min": 0.10028899999999999, "max": 0.19924999999999993, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20057799999999998, "min": 0.10254, "max": 0.39336799999999994, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 3.887110000000003e-05, "min": 3.887110000000003e-05, "max": 0.009925074999999997, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 7.774220000000006e-05, "min": 7.774220000000006e-05, "max": 0.0193374632, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.005907778681916601, "min": 0.005171077248329918, "max": 0.3516008852957151, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.011815557363833202, "min": 0.005171077248329918, "max": 0.3516008852957151, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.8244420469550953, "min": 3.732571636504243, "max": 4.390753862185356, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.6488840939101905, "min": 3.736011778866803, "max": 8.560909711796306, "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": "1716667366", "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_7_task_1_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_7_task_1_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": "1716669282" }, "total": 1916.3543140000002, "count": 1, "self": 0.20027280000022074, "children": { "run_training.setup": { "total": 0.0532956, "count": 1, "self": 0.0532956 }, "TrainerController.start_learning": { "total": 1916.1007456, "count": 1, "self": 1.2124744000045666, "children": { "TrainerController._reset_env": { "total": 2.1096662, "count": 1, "self": 2.1096662 }, "TrainerController.advance": { "total": 1912.6821870999956, "count": 50136, "self": 0.9964985999811233, "children": { "env_step": { "total": 1911.6856885000145, "count": 50136, "self": 1633.4743607000073, "children": { "SubprocessEnvManager._take_step": { "total": 277.7303721999926, "count": 50136, "self": 1.7871896999790806, "children": { "TorchPolicy.evaluate": { "total": 275.9431825000135, "count": 50136, "self": 275.9431825000135 } } }, "workers": { "total": 0.48095560001450854, "count": 50136, "self": 0.0, "children": { "worker_root": { "total": 1913.4493875999985, "count": 50136, "is_parallel": true, "self": 340.3863610999763, "children": { "steps_from_proto": { "total": 0.0002394999999999481, "count": 1, "is_parallel": true, "self": 0.00011400000000016952, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012549999999977857, "count": 2, "is_parallel": true, "self": 0.00012549999999977857 } } }, "UnityEnvironment.step": { "total": 1573.0627870000224, "count": 50136, "is_parallel": true, "self": 3.4146254000422687, "children": { "UnityEnvironment._generate_step_input": { "total": 4.22944119999039, "count": 50136, "is_parallel": true, "self": 4.22944119999039 }, "communicator.exchange": { "total": 1555.4927993000078, "count": 50136, "is_parallel": true, "self": 1555.4927993000078 }, "steps_from_proto": { "total": 9.925921099981919, "count": 50136, "is_parallel": true, "self": 4.999919899978398, "children": { "_process_rank_one_or_two_observation": { "total": 4.926001200003521, "count": 100272, "is_parallel": true, "self": 4.926001200003521 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.2099999796409975e-05, "count": 1, "self": 2.2099999796409975e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1912.6062513000165, "count": 97830, "is_parallel": true, "self": 3.4296286000389955, "children": { "process_trajectory": { "total": 1551.7061777999797, "count": 97830, "is_parallel": true, "self": 1551.7061777999797 }, "_update_policy": { "total": 357.47044489999786, "count": 151, "is_parallel": true, "self": 175.59495200000754, "children": { "TorchPPOOptimizer.update": { "total": 181.87549289999032, "count": 10320, "is_parallel": true, "self": 181.87549289999032 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09639579999998205, "count": 1, "self": 0.004710700000032375, "children": { "RLTrainer._checkpoint": { "total": 0.09168509999994967, "count": 1, "self": 0.09168509999994967 } } } } } } }