{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 4.10906457901001, "min": 3.953599691390991, "max": 4.382236480712891, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 20154.9609375, "min": 6310.353515625, "max": 33243.51953125, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.84074066137826, "min": 0.580555564413468, "max": 0.8833331788579623, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 22.69999785721302, "min": 6.299999736249447, "max": 37.100000493228436, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 62.94793286146941, "min": 2.1126839800013437, "max": 174.3156435224745, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 1699.594187259674, "min": 19.014155820012093, "max": 2777.7045707702637, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 5.5113346623601736, "min": 0.10728350813345362, "max": 32.28754201262362, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 148.8060358837247, "min": 0.9655515732010826, "max": 581.1757562272251, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 48.54119604605216, "min": 10.442443953620064, "max": 131.98800998263889, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1310.6122932434082, "min": 93.98199558258057, "max": 2520.427713394165, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 24.993142541911865, "min": 3.9258375565210977, "max": 67.30801399548848, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 674.8148486316204, "min": 35.33253800868988, "max": 1183.1424649953842, "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": 181.66666666666666, "min": 96.33333333333333, "max": 473.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 4905.0, "min": 1512.0, "max": 7803.0, "count": 100 }, "Agent.Step.mean": { "value": 449977.0, "min": 4405.0, "max": 449977.0, "count": 100 }, "Agent.Step.sum": { "value": 449977.0, "min": 4405.0, "max": 449977.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.005271104164421558, "min": 0.0028119045309722424, "max": 0.10121196508407593, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.10542207956314087, "min": 0.03655475750565529, "max": 2.9892563819885254, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 46.583866119384766, "min": 1.4095145463943481, "max": 50.10201644897461, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 931.6773071289062, "min": 36.647377014160156, "max": 1440.863037109375, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 130.25334053039552, "min": 34.908504210985626, "max": 299.47864948619497, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 2605.06681060791, "min": 851.9657640457153, "max": 4545.484237670898, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.014984373934566975, "min": 0.012029563623440006, "max": 0.27463194438152844, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.2996874786913395, "min": 0.27667996333912015, "max": 5.141282767057419, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 130.25334053039552, "min": 34.908504210985626, "max": 299.47864948619497, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 2605.06681060791, "min": 851.9657640457153, "max": 4545.484237670898, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.07050818018041988, "min": 0.051242445733536174, "max": 0.08576969407937106, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14101636036083975, "min": 0.051242445733536174, "max": 0.15651646077943343, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 148.40672881856108, "min": 7.167425623646489, "max": 194.00161840045263, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 296.81345763712216, "min": 7.167425623646489, "max": 296.81345763712216, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.4610995129999955e-06, "min": 1.4610995129999955e-06, "max": 0.00029848200050600006, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 2.922199025999991e-06, "min": 2.922199025999991e-06, "max": 0.0005858280047239997, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10048699999999999, "min": 0.10048699999999999, "max": 0.199494, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20097399999999999, "min": 0.101576, "max": 0.3952760000000001, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 5.865129999999986e-05, "min": 5.865129999999986e-05, "max": 0.009949450600000001, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00011730259999999973, "min": 0.00011730259999999973, "max": 0.0195280724, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0029302960296208216, "min": 0.0028792914856846136, "max": 0.4862046896242628, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.005860592059241643, "min": 0.0028792914856846136, "max": 0.4862046896242628, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 4.06954655728557, "min": 3.951764164826809, "max": 4.390673973981072, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 8.13909311457114, "min": 3.99115928279029, "max": 8.732504906730046, "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": "1716698425", "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_3_task_0_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_3_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": "1716700134" }, "total": 1709.785834, "count": 1, "self": 0.1950813000000835, "children": { "run_training.setup": { "total": 0.05489809999999995, "count": 1, "self": 0.05489809999999995 }, "TrainerController.start_learning": { "total": 1709.5358546, "count": 1, "self": 1.130918400007431, "children": { "TrainerController._reset_env": { "total": 2.0991529, "count": 1, "self": 2.0991529 }, "TrainerController.advance": { "total": 1706.2142064999925, "count": 50074, "self": 1.0481499999768857, "children": { "env_step": { "total": 1705.1660565000157, "count": 50074, "self": 1430.9222537000057, "children": { "SubprocessEnvManager._take_step": { "total": 273.7635207000144, "count": 50074, "self": 1.7298472000317133, "children": { "TorchPolicy.evaluate": { "total": 272.0336734999827, "count": 50074, "self": 272.0336734999827 } } }, "workers": { "total": 0.480282099995482, "count": 50074, "self": 0.0, "children": { "worker_root": { "total": 1706.9549295999832, "count": 50074, "is_parallel": true, "self": 334.01458839997554, "children": { "steps_from_proto": { "total": 0.00023960000000000647, "count": 1, "is_parallel": true, "self": 0.00011570000000005187, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001238999999999546, "count": 2, "is_parallel": true, "self": 0.0001238999999999546 } } }, "UnityEnvironment.step": { "total": 1372.9401016000077, "count": 50074, "is_parallel": true, "self": 3.207720599995355, "children": { "UnityEnvironment._generate_step_input": { "total": 4.088172499985037, "count": 50074, "is_parallel": true, "self": 4.088172499985037 }, "communicator.exchange": { "total": 1356.187570600013, "count": 50074, "is_parallel": true, "self": 1356.187570600013 }, "steps_from_proto": { "total": 9.456637900014167, "count": 50074, "is_parallel": true, "self": 4.884551600035019, "children": { "_process_rank_one_or_two_observation": { "total": 4.572086299979148, "count": 100148, "is_parallel": true, "self": 4.572086299979148 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.0599999970727367e-05, "count": 1, "self": 2.0599999970727367e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1706.297710800034, "count": 84235, "is_parallel": true, "self": 2.7666425000472827, "children": { "process_trajectory": { "total": 1338.2803008999865, "count": 84235, "is_parallel": true, "self": 1338.2803008999865 }, "_update_policy": { "total": 365.25076740000037, "count": 141, "is_parallel": true, "self": 178.0320376000104, "children": { "TorchPPOOptimizer.update": { "total": 187.21872979998997, "count": 10335, "is_parallel": true, "self": 187.21872979998997 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09155620000001363, "count": 1, "self": 0.005480400000124064, "children": { "RLTrainer._checkpoint": { "total": 0.08607579999988957, "count": 1, "self": 0.08607579999988957 } } } } } } }