{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 1.0432231426239014, "min": 0.8955050706863403, "max": 1.095898985862732, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 41770.65234375, "min": 35848.859375, "max": 43897.328125, "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": 9.18587875366211, "min": 0.5215618014335632, "max": 9.54175090789795, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 220.46109008789062, "min": 12.51748275756836, "max": 229.00201416015625, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.049005920570163564, "min": 0.044099667442972695, "max": 0.053326188027096495, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.1470177617104907, "min": 0.10106326845076788, "max": 0.1599785640812895, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.2060797198029745, "min": 0.06279220564188324, "max": 1.518491332186386, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.6182391594089235, "min": 0.18837661692564975, "max": 3.036982664372772, "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": 4558.020690917969, "min": 446.97447872161865, "max": 4685.875671386719, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.sum": { "value": 36464.16552734375, "min": 3575.795829772949, "max": 37487.00537109375, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4554.759002685547, "min": 470.43567184761196, "max": 4676.411651611328, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 36438.072021484375, "min": 3763.4853747808957, "max": 37411.293212890625, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4554.759002685547, "min": 470.43567184761196, "max": 4676.411651611328, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 36438.072021484375, "min": 3763.4853747808957, "max": 37411.293212890625, "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": "1715328384", "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_0_run_id_2_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_5_task_0_run_id_2_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": "1715331990" }, "total": 3606.0257179, "count": 1, "self": 0.16022790000033638, "children": { "run_training.setup": { "total": 0.04490939999999999, "count": 1, "self": 0.04490939999999999 }, "TrainerController.start_learning": { "total": 3605.8205805999996, "count": 1, "self": 10.519716600265838, "children": { "TrainerController._reset_env": { "total": 1.6028524, "count": 1, "self": 1.6028524 }, "TrainerController.advance": { "total": 3593.672235099734, "count": 1002054, "self": 9.436604299632563, "children": { "env_step": { "total": 3584.2356308001013, "count": 1002054, "self": 1487.7461318999108, "children": { "SubprocessEnvManager._take_step": { "total": 2090.800368300095, "count": 1002054, "self": 25.431422900004236, "children": { "TorchPolicy.evaluate": { "total": 2065.368945400091, "count": 1002054, "self": 2065.368945400091 } } }, "workers": { "total": 5.68913060009508, "count": 1002054, "self": 0.0, "children": { "worker_root": { "total": 3592.593155399929, "count": 1002054, "is_parallel": true, "self": 2738.5719981999655, "children": { "steps_from_proto": { "total": 0.000260000000000038, "count": 1, "is_parallel": true, "self": 0.00012149999999999661, "children": { "_process_rank_one_or_two_observation": { "total": 0.00013850000000004137, "count": 2, "is_parallel": true, "self": 0.00013850000000004137 } } }, "UnityEnvironment.step": { "total": 854.0208971999637, "count": 1002054, "is_parallel": true, "self": 42.11394360005306, "children": { "UnityEnvironment._generate_step_input": { "total": 62.361521299834585, "count": 1002054, "is_parallel": true, "self": 62.361521299834585 }, "communicator.exchange": { "total": 631.7332501999549, "count": 1002054, "is_parallel": true, "self": 631.7332501999549 }, "steps_from_proto": { "total": 117.81218210012103, "count": 1002054, "is_parallel": true, "self": 65.76215430011845, "children": { "_process_rank_one_or_two_observation": { "total": 52.05002780000258, "count": 2004108, "is_parallel": true, "self": 52.05002780000258 } } } } } } } } } } } } }, "trainer_threads": { "total": 1.8700000055105193e-05, "count": 1, "self": 1.8700000055105193e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3603.3099547000866, "count": 106489, "is_parallel": true, "self": 4.505542100119783, "children": { "process_trajectory": { "total": 1857.001655799972, "count": 106489, "is_parallel": true, "self": 1856.591344499972, "children": { "RLTrainer._checkpoint": { "total": 0.4103113000001031, "count": 16, "is_parallel": true, "self": 0.4103113000001031 } } }, "_update_policy": { "total": 1741.8027567999948, "count": 600, "is_parallel": true, "self": 572.0102799999847, "children": { "TorchPPOOptimizer.update": { "total": 1169.79247680001, "count": 93600, "is_parallel": true, "self": 1169.79247680001 } } } } } } } } }, "TrainerController._save_models": { "total": 0.02575780000006489, "count": 1, "self": 0.005545900000015536, "children": { "RLTrainer._checkpoint": { "total": 0.020211900000049354, "count": 1, "self": 0.020211900000049354 } } } } } } }