{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.907257556915283, "min": 3.8194007873535156, "max": 4.383535385131836, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 10233.107421875, "min": 7948.7470703125, "max": 27558.85546875, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8722221093873183, "min": 0.5527778211981058, "max": 0.8944443114515808, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 15.69999796897173, "min": 7.100000753998756, "max": 32.19999521225691, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 20.876815729671055, "min": 12.896453539530436, "max": 95.38418918185764, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 375.782683134079, "min": 251.21033477783203, "max": 1525.620590209961, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 4.164082578111877, "min": 0.5644464592742561, "max": 15.06212878641155, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 74.95348640601378, "min": 13.828007256612182, "max": 271.4700351841748, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 27.33929549323188, "min": 22.169620566897922, "max": 130.48260328504773, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 492.1073188781738, "min": 481.04047775268555, "max": 2108.3874168395996, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 12.977867441044914, "min": 10.525023167745935, "max": 65.73048403528001, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 233.60161393880844, "min": 221.44261133670807, "max": 934.4875229597092, "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": 144.5, "min": 110.5, "max": 483.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 2601.0, "min": 2034.0, "max": 6606.0, "count": 100 }, "Agent.Step.mean": { "value": 449971.0, "min": 4406.0, "max": 449971.0, "count": 100 }, "Agent.Step.sum": { "value": 449971.0, "min": 4406.0, "max": 449971.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.00013608139124698937, "min": -0.010359995067119598, "max": 0.10701742768287659, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.002857709303498268, "min": -0.19373363256454468, "max": 1.8192962408065796, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 27.973678588867188, "min": 1.6554384231567383, "max": 41.58695983886719, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 587.447265625, "min": 31.453330993652344, "max": 1234.9969482421875, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 68.89549400692894, "min": 40.027601392645586, "max": 217.93534989790484, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 1446.8053741455078, "min": 1129.5475368499756, "max": 3360.4785079956055, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.017490419071345104, "min": 0.011719846607160729, "max": 0.1923424754291773, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.36729880049824715, "min": 0.2767012189142406, "max": 3.8468495085835457, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 68.89549400692894, "min": 40.027601392645586, "max": 217.93534989790484, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 1446.8053741455078, "min": 1129.5475368499756, "max": 3360.4785079956055, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.07554966094593207, "min": 0.05716271330511161, "max": 0.0825922567769885, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.07554966094593207, "min": 0.05716271330511161, "max": 0.1624291412676302, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 33.64323465983073, "min": 5.6186702781253395, "max": 88.00010821861133, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 33.64323465983073, "min": 5.6186702781253395, "max": 176.00021643722266, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.3200995599999879e-06, "min": 1.3200995599999879e-06, "max": 0.0002979480006839999, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 1.3200995599999879e-06, "min": 1.3200995599999879e-06, "max": 0.0005902860032380002, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10043999999999999, "min": 0.10043999999999999, "max": 0.19931600000000002, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.10043999999999999, "min": 0.10043999999999999, "max": 0.3967619999999999, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 5.395599999999961e-05, "min": 5.395599999999961e-05, "max": 0.009931668400000001, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 5.395599999999961e-05, "min": 5.395599999999961e-05, "max": 0.019676523799999995, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0029377577236543097, "min": 0.0028678242294561296, "max": 0.3038852005783055, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.0029377577236543097, "min": 0.0028678242294561296, "max": 0.3038852005783055, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.888281815846761, "min": 3.7724405563238896, "max": 4.390625682142046, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 3.888281815846761, "min": 3.7724405563238896, "max": 8.739023064810132, "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": "1716737515", "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_10_task_0_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_10_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": "1716739459" }, "total": 1944.2246961, "count": 1, "self": 0.1992193999999472, "children": { "run_training.setup": { "total": 0.051543500000000075, "count": 1, "self": 0.051543500000000075 }, "TrainerController.start_learning": { "total": 1943.9739332000001, "count": 1, "self": 1.335295300005555, "children": { "TrainerController._reset_env": { "total": 3.8213012, "count": 1, "self": 3.8213012 }, "TrainerController.advance": { "total": 1938.6839051999946, "count": 50073, "self": 1.1214994999784267, "children": { "env_step": { "total": 1937.5624057000161, "count": 50073, "self": 1630.55597800001, "children": { "SubprocessEnvManager._take_step": { "total": 306.4660056999909, "count": 50073, "self": 1.9966946999949187, "children": { "TorchPolicy.evaluate": { "total": 304.46931099999597, "count": 50073, "self": 304.46931099999597 } } }, "workers": { "total": 0.5404220000151332, "count": 50073, "self": 0.0, "children": { "worker_root": { "total": 1939.511698400012, "count": 50073, "is_parallel": true, "self": 378.506883800007, "children": { "steps_from_proto": { "total": 0.00027439999999989695, "count": 1, "is_parallel": true, "self": 0.00012280000000020053, "children": { "_process_rank_one_or_two_observation": { "total": 0.00015159999999969642, "count": 2, "is_parallel": true, "self": 0.00015159999999969642 } } }, "UnityEnvironment.step": { "total": 1561.0045402000048, "count": 50073, "is_parallel": true, "self": 4.14460230001464, "children": { "UnityEnvironment._generate_step_input": { "total": 5.6658294999797425, "count": 50073, "is_parallel": true, "self": 5.6658294999797425 }, "communicator.exchange": { "total": 1539.4374163999985, "count": 50073, "is_parallel": true, "self": 1539.4374163999985 }, "steps_from_proto": { "total": 11.75669200001192, "count": 50073, "is_parallel": true, "self": 6.1512728000214905, "children": { "_process_rank_one_or_two_observation": { "total": 5.60541919999043, "count": 100146, "is_parallel": true, "self": 5.60541919999043 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.300000005561742e-05, "count": 1, "self": 2.300000005561742e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1938.730705200026, "count": 95256, "is_parallel": true, "self": 3.5688045000138118, "children": { "process_trajectory": { "total": 1516.5420195000117, "count": 95256, "is_parallel": true, "self": 1516.5420195000117 }, "_update_policy": { "total": 418.61988120000035, "count": 143, "is_parallel": true, "self": 206.29256320000087, "children": { "TorchPPOOptimizer.update": { "total": 212.32731799999948, "count": 10281, "is_parallel": true, "self": 212.32731799999948 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1334084999998595, "count": 1, "self": 0.005799599999818383, "children": { "RLTrainer._checkpoint": { "total": 0.1276089000000411, "count": 1, "self": 0.1276089000000411 } } } } } } }