{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.9218742847442627, "min": 3.863060474395752, "max": 4.382823467254639, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 21354.60546875, "min": 8286.625, "max": 31645.068359375, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8733334170447455, "min": 0.650000056044923, "max": 0.8888889882299635, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 39.30000376701355, "min": 7.100000649690628, "max": 61.100006096065044, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 1.7044366454084714, "min": 0.43675118446764016, "max": 14.50437198082606, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 76.69964904338121, "min": 13.791587144136429, "max": 404.41131377220154, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 138.11908293565114, "min": 15.732518797671354, "max": 485.51227484809027, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 6215.358732104301, "min": 849.5560150742531, "max": 8050.53844833374, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 31.67512978447808, "min": 14.841589812879208, "max": 114.47105407714844, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1425.3808403015137, "min": 529.9125142097473, "max": 2131.192500114441, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 16.451286547879377, "min": 6.683963431252374, "max": 57.487370596991646, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 740.307894654572, "min": 230.80473151803017, "max": 1005.2699508666992, "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": 120.2, "min": 65.16666666666667, "max": 436.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 5409.0, "min": 2052.0, "max": 7722.0, "count": 100 }, "Agent.Step.mean": { "value": 449904.0, "min": 4441.0, "max": 449904.0, "count": 100 }, "Agent.Step.sum": { "value": 449904.0, "min": 4441.0, "max": 449904.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.01566745899617672, "min": -0.04759064316749573, "max": 0.1646767556667328, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.6580332517623901, "min": -1.878260850906372, "max": 4.296153545379639, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 85.21717834472656, "min": 0.376181960105896, "max": 99.24287414550781, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 3579.121337890625, "min": 15.423460960388184, "max": 3766.849853515625, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 165.82417479015533, "min": 34.71144700631863, "max": 534.9340178171793, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 6964.615341186523, "min": 1423.1693272590637, "max": 8177.103809833527, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.018203601307634796, "min": 0.014499624579477666, "max": 0.18180511673776115, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.7645512549206614, "min": 0.4937439579516649, "max": 7.454009786248207, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 165.82417479015533, "min": 34.71144700631863, "max": 534.9340178171793, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 6964.615341186523, "min": 1423.1693272590637, "max": 8177.103809833527, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06870737995969312, "min": 0.055507686713503465, "max": 0.08021375311013215, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.13741475991938623, "min": 0.055507686713503465, "max": 0.2052263682775899, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 934.7500864268123, "min": 12.23641684320238, "max": 934.7500864268123, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 1869.5001728536247, "min": 12.23641684320238, "max": 1869.5001728536247, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.6080994640000096e-06, "min": 1.6080994640000096e-06, "max": 0.00029842200052599994, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 3.216198928000019e-06, "min": 3.216198928000019e-06, "max": 0.0005854140048619999, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10053600000000001, "min": 0.10053600000000001, "max": 0.19947400000000004, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20107200000000003, "min": 0.101584, "max": 0.490534, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 6.354640000000032e-05, "min": 6.354640000000032e-05, "max": 0.009947452599999998, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00012709280000000063, "min": 0.00012709280000000063, "max": 0.0195142862, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.007479374189700755, "min": 0.004942750531262246, "max": 0.37563059092671786, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.01495874837940151, "min": 0.004942750531262246, "max": 0.37563059092671786, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.7495019280190123, "min": 3.7219206725849823, "max": 4.390431465925993, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.4990038560380246, "min": 3.7219206725849823, "max": 12.085247370206488, "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": "1716635595", "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_1_task_1_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_1_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": "1716637228" }, "total": 1632.6059326, "count": 1, "self": 0.21384130000001278, "children": { "run_training.setup": { "total": 0.05671159999999997, "count": 1, "self": 0.05671159999999997 }, "TrainerController.start_learning": { "total": 1632.3353797, "count": 1, "self": 1.204931100003705, "children": { "TrainerController._reset_env": { "total": 2.1452037, "count": 1, "self": 2.1452037 }, "TrainerController.advance": { "total": 1628.8838285999961, "count": 50201, "self": 0.9999493999921469, "children": { "env_step": { "total": 1627.883879200004, "count": 50201, "self": 1356.462256299996, "children": { "SubprocessEnvManager._take_step": { "total": 270.95744470000267, "count": 50201, "self": 1.7378636999908963, "children": { "TorchPolicy.evaluate": { "total": 269.2195810000118, "count": 50201, "self": 269.2195810000118 } } }, "workers": { "total": 0.4641782000053478, "count": 50201, "self": 0.0, "children": { "worker_root": { "total": 1629.7476933999687, "count": 50201, "is_parallel": true, "self": 332.937152899965, "children": { "steps_from_proto": { "total": 0.00024489999999999235, "count": 1, "is_parallel": true, "self": 0.0001184999999996883, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012640000000030405, "count": 2, "is_parallel": true, "self": 0.00012640000000030405 } } }, "UnityEnvironment.step": { "total": 1296.8102956000037, "count": 50201, "is_parallel": true, "self": 3.2137171999620477, "children": { "UnityEnvironment._generate_step_input": { "total": 4.057409000002163, "count": 50201, "is_parallel": true, "self": 4.057409000002163 }, "communicator.exchange": { "total": 1279.9483216000249, "count": 50201, "is_parallel": true, "self": 1279.9483216000249 }, "steps_from_proto": { "total": 9.590847800014732, "count": 50201, "is_parallel": true, "self": 4.8921236000355, "children": { "_process_rank_one_or_two_observation": { "total": 4.698724199979232, "count": 100402, "is_parallel": true, "self": 4.698724199979232 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.0500000118772732e-05, "count": 1, "self": 2.0500000118772732e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1629.2049924999953, "count": 78999, "is_parallel": true, "self": 2.4634891000175685, "children": { "process_trajectory": { "total": 1259.2101674999785, "count": 78999, "is_parallel": true, "self": 1259.2101674999785 }, "_update_policy": { "total": 367.53133589999936, "count": 150, "is_parallel": true, "self": 179.1598848999912, "children": { "TorchPPOOptimizer.update": { "total": 188.37145100000816, "count": 10314, "is_parallel": true, "self": 188.37145100000816 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10139580000009119, "count": 1, "self": 0.015529600000036226, "children": { "RLTrainer._checkpoint": { "total": 0.08586620000005496, "count": 1, "self": 0.08586620000005496 } } } } } } }