{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.8463598489761353, "min": 0.6719727516174316, "max": 1.0956945419311523, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 33854.39453125, "min": 26900.412109375, "max": 43889.140625, "count": 200 }, "Agent.Environment.LessonNumber.pattern.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Environment.LessonNumber.pattern.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Environment.LessonNumber.task.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Environment.LessonNumber.task.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Step.mean": { "value": 7999096.0, "min": 39096.0, "max": 7999096.0, "count": 200 }, "Agent.Step.sum": { "value": 7999096.0, "min": 39096.0, "max": 7999096.0, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 9.698019981384277, "min": 2.4821584224700928, "max": 9.835981369018555, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 232.75247192382812, "min": 57.08964157104492, "max": 236.0635528564453, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.05006786484972551, "min": 0.04407803850393513, "max": 0.05430137651458767, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.15020359454917653, "min": 0.10292157364407709, "max": 0.18532924180839297, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.004923122996987086, "min": 0.003196629786514908, "max": 3.8035268960520625, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.014769368990961257, "min": 0.009589889359544725, "max": 8.826118394466384, "count": 200 }, "Agent.Policy.LearningRate.mean": { "value": 8.856997047999973e-07, "min": 8.856997047999973e-07, "max": 0.00029907840030719997, "count": 200 }, "Agent.Policy.LearningRate.sum": { "value": 2.657099114399992e-06, "min": 2.657099114399992e-06, "max": 0.0008936568021144, "count": 200 }, "Agent.Policy.Epsilon.mean": { "value": 0.10029520000000001, "min": 0.10029520000000001, "max": 0.1996928, "count": 200 }, "Agent.Policy.Epsilon.sum": { "value": 0.30088560000000003, "min": 0.30088560000000003, "max": 0.5978856, "count": 200 }, "Agent.Policy.Beta.mean": { "value": 2.4730479999999958e-05, "min": 2.4730479999999958e-05, "max": 0.004984670720000001, "count": 200 }, "Agent.Policy.Beta.sum": { "value": 7.419143999999988e-05, "min": 7.419143999999988e-05, "max": 0.014894491440000001, "count": 200 }, "Agent.Environment.EpisodeLength.mean": { "value": 4999.0, "min": 4999.0, "max": 4999.0, "count": 200 }, "Agent.Environment.EpisodeLength.sum": { "value": 39992.0, "min": 39992.0, "max": 39992.0, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.mean": { "value": 4821.4154052734375, "min": 1815.2337341308594, "max": 4890.1783447265625, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 38571.3232421875, "min": 14521.869873046875, "max": 39121.4267578125, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4840.562797546387, "min": 1952.195821762085, "max": 4883.699890136719, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 38724.502380371094, "min": 15617.56657409668, "max": 39069.59912109375, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4840.562797546387, "min": 1952.195821762085, "max": 4883.699890136719, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 38724.502380371094, "min": 15617.56657409668, "max": 39069.59912109375, "count": 200 }, "Agent.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Agent.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715261386", "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/WindFarmControl_pattern_5_task_1_run_id_1_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_5_task_1_run_id_1_train", "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": "1.21.2", "end_time_seconds": "1715265316" }, "total": 3929.7966452, "count": 1, "self": 0.17198839999991833, "children": { "run_training.setup": { "total": 0.044641199999999936, "count": 1, "self": 0.044641199999999936 }, "TrainerController.start_learning": { "total": 3929.5800156, "count": 1, "self": 10.863572300274427, "children": { "TrainerController._reset_env": { "total": 1.5886935000000002, "count": 1, "self": 1.5886935000000002 }, "TrainerController.advance": { "total": 3917.100298099726, "count": 1002052, "self": 10.045437599807428, "children": { "env_step": { "total": 3907.0548604999185, "count": 1002052, "self": 1708.4704037000774, "children": { "SubprocessEnvManager._take_step": { "total": 2192.787355999813, "count": 1002052, "self": 26.516677899759998, "children": { "TorchPolicy.evaluate": { "total": 2166.270678100053, "count": 1002052, "self": 2166.270678100053 } } }, "workers": { "total": 5.797100800028174, "count": 1002052, "self": 0.0, "children": { "worker_root": { "total": 3912.614743600048, "count": 1002052, "is_parallel": true, "self": 2882.595832400273, "children": { "steps_from_proto": { "total": 0.00023850000000003035, "count": 1, "is_parallel": true, "self": 0.00010980000000004875, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001286999999999816, "count": 2, "is_parallel": true, "self": 0.0001286999999999816 } } }, "UnityEnvironment.step": { "total": 1030.018672699775, "count": 1002052, "is_parallel": true, "self": 55.92269649927482, "children": { "UnityEnvironment._generate_step_input": { "total": 87.83036260007455, "count": 1002052, "is_parallel": true, "self": 87.83036260007455 }, "communicator.exchange": { "total": 738.3862840002357, "count": 1002052, "is_parallel": true, "self": 738.3862840002357 }, "steps_from_proto": { "total": 147.87932960018986, "count": 1002052, "is_parallel": true, "self": 83.3139199003077, "children": { "_process_rank_one_or_two_observation": { "total": 64.56540969988217, "count": 2004104, "is_parallel": true, "self": 64.56540969988217 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.2599999738304177e-05, "count": 1, "self": 2.2599999738304177e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3927.0883546999585, "count": 115988, "is_parallel": true, "self": 4.387345499979801, "children": { "process_trajectory": { "total": 2032.672234899977, "count": 115988, "is_parallel": true, "self": 2032.2386188999767, "children": { "RLTrainer._checkpoint": { "total": 0.43361600000037015, "count": 16, "is_parallel": true, "self": 0.43361600000037015 } } }, "_update_policy": { "total": 1890.0287743000017, "count": 601, "is_parallel": true, "self": 570.1221957999956, "children": { "TorchPPOOptimizer.update": { "total": 1319.9065785000062, "count": 93600, "is_parallel": true, "self": 1319.9065785000062 } } } } } } } } }, "TrainerController._save_models": { "total": 0.027429100000063045, "count": 1, "self": 0.0068734999999833235, "children": { "RLTrainer._checkpoint": { "total": 0.02055560000007972, "count": 1, "self": 0.02055560000007972 } } } } } } }