{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.8250205516815186, "min": 3.781966209411621, "max": 4.3849077224731445, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 31774.4453125, "min": 3811.70068359375, "max": 31774.4453125, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8749998913456997, "min": 0.5977778246005376, "max": 0.8999999132421281, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 31.499996088445187, "min": 7.2999982088804245, "max": 39.699994653463364, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 64.37658325831096, "min": 6.998928799894121, "max": 226.0948363410102, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 2317.5569972991943, "min": 192.43605275452137, "max": 4069.7070541381836, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 2.4944586501563513, "min": 0.38754652109411025, "max": 23.108198947376675, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 89.80051140562864, "min": 3.4879186898469925, "max": 307.4278855025768, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 55.43790119224124, "min": 23.547830939292908, "max": 134.51567925347223, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1995.7644429206848, "min": 277.8177375793457, "max": 2421.2822265625, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 27.929693864865435, "min": 10.03525119357639, "max": 77.37440181440778, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 1005.4689791351557, "min": 113.71414232254028, "max": 1392.73923265934, "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": 230.5, "min": 89.6, "max": 499.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 8298.0, "min": 936.0, "max": 8298.0, "count": 100 }, "Agent.Step.mean": { "value": 449883.0, "min": 4251.0, "max": 449883.0, "count": 100 }, "Agent.Step.sum": { "value": 449883.0, "min": 4251.0, "max": 449883.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.0036401022225618362, "min": -0.006736040581017733, "max": 0.09403384476900101, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.1055629625916481, "min": -0.16166497766971588, "max": 2.263749122619629, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 48.578224182128906, "min": 0.6429362297058105, "max": 51.2713623046875, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 1408.7685546875, "min": 21.216896057128906, "max": 1913.24609375, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 116.04774184884697, "min": 34.79026948439108, "max": 353.71294530232746, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 3365.384513616562, "min": 1287.23997092247, "max": 4514.866436004639, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.01064677479885647, "min": 0.0105968882155139, "max": 0.15601867911490527, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.30875646916683763, "min": 0.21361754927784204, "max": 3.6611265898682177, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 116.04774184884697, "min": 34.79026948439108, "max": 353.71294530232746, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 3365.384513616562, "min": 1287.23997092247, "max": 4514.866436004639, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06706821041276541, "min": 0.05490083507923545, "max": 0.08253337718188708, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.13413642082553082, "min": 0.05490083507923545, "max": 0.16506675436377416, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 189.11538977093167, "min": 8.655427361712043, "max": 247.30803502400715, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 378.23077954186334, "min": 8.655427361712043, "max": 378.23077954186334, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.827099390999995e-06, "min": 1.827099390999995e-06, "max": 0.00029819400060199984, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 3.65419878199999e-06, "min": 3.65419878199999e-06, "max": 0.0005916540027819999, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.100609, "min": 0.100609, "max": 0.19939800000000005, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.201218, "min": 0.10158800000000001, "max": 0.39721799999999996, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 7.083909999999983e-05, "min": 7.083909999999983e-05, "max": 0.009939860200000004, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00014167819999999967, "min": 0.00014167819999999967, "max": 0.0197220782, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.002516701049494764, "min": 0.0024789777889065905, "max": 0.3829007114446352, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.005033402098989528, "min": 0.0024789777889065905, "max": 0.3829007114446352, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.866822721229659, "min": 3.785426095922165, "max": 4.3893865706428645, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.733645442459318, "min": 3.794241119314123, "max": 8.721520320713868, "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": "1716748207", "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_2_task_0_run_id_2_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_task_0_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": "1716749871" }, "total": 1664.2690427, "count": 1, "self": 0.19599360000006527, "children": { "run_training.setup": { "total": 0.05776839999999994, "count": 1, "self": 0.05776839999999994 }, "TrainerController.start_learning": { "total": 1664.0152807, "count": 1, "self": 1.2582331000037357, "children": { "TrainerController._reset_env": { "total": 2.2044389, "count": 1, "self": 2.2044389 }, "TrainerController.advance": { "total": 1660.4672068999964, "count": 50488, "self": 1.026647999997067, "children": { "env_step": { "total": 1659.4405588999994, "count": 50488, "self": 1381.3322238000187, "children": { "SubprocessEnvManager._take_step": { "total": 277.6351163999923, "count": 50488, "self": 1.7669153999772789, "children": { "TorchPolicy.evaluate": { "total": 275.868201000015, "count": 50488, "self": 275.868201000015 } } }, "workers": { "total": 0.473218699988355, "count": 50488, "self": 0.0, "children": { "worker_root": { "total": 1661.2741138000229, "count": 50488, "is_parallel": true, "self": 337.7463708000421, "children": { "steps_from_proto": { "total": 0.00024679999999999147, "count": 1, "is_parallel": true, "self": 0.00012110000000009613, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012569999999989534, "count": 2, "is_parallel": true, "self": 0.00012569999999989534 } } }, "UnityEnvironment.step": { "total": 1323.5274961999808, "count": 50488, "is_parallel": true, "self": 3.319581699994842, "children": { "UnityEnvironment._generate_step_input": { "total": 3.9830209999916737, "count": 50488, "is_parallel": true, "self": 3.9830209999916737 }, "communicator.exchange": { "total": 1306.6126863999732, "count": 50488, "is_parallel": true, "self": 1306.6126863999732 }, "steps_from_proto": { "total": 9.612207100021052, "count": 50488, "is_parallel": true, "self": 4.936334900004079, "children": { "_process_rank_one_or_two_observation": { "total": 4.675872200016974, "count": 100976, "is_parallel": true, "self": 4.675872200016974 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.099999983329326e-05, "count": 1, "self": 2.099999983329326e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1660.7519113999886, "count": 81365, "is_parallel": true, "self": 2.652982099989231, "children": { "process_trajectory": { "total": 1291.9234196999992, "count": 81365, "is_parallel": true, "self": 1291.9234196999992 }, "_update_policy": { "total": 366.17550960000005, "count": 147, "is_parallel": true, "self": 178.23394200000234, "children": { "TorchPPOOptimizer.update": { "total": 187.9415675999977, "count": 10305, "is_parallel": true, "self": 187.9415675999977 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08538079999993897, "count": 1, "self": 0.004887399999915942, "children": { "RLTrainer._checkpoint": { "total": 0.08049340000002303, "count": 1, "self": 0.08049340000002303 } } } } } } }