本文整理汇总了Python中simulator.Simulator.options['SARSA']['useSupervisedTraining']方法的典型用法代码示例。如果您正苦于以下问题：Python Simulator.options['SARSA']['useSupervisedTraining']方法的具体用法？Python Simulator.options['SARSA']['useSupervisedTraining']怎么用？Python Simulator.options['SARSA']['useSupervisedTraining']使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类simulator.Simulator的用法示例。
在下文中一共展示了Simulator.options['SARSA']['useSupervisedTraining']方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: Simulator
# 需要导入模块: from simulator import Simulator [as 别名]
# 或者: from simulator.Simulator import options['SARSA']['useSupervisedTraining'] [as 别名]
__author__ = 'manuelli'
from simulator import Simulator
sim = Simulator(autoInitialize=False, verbose=False)
sim.sarsaType = "discrete"
sim.options['SARSA']['lam'] = 0.0
sim.options['SARSA']['useQLearningUpdate'] = True
sim.options['SARSA']['numInnerBins'] = 5
sim.options['SARSA']['numOuterBins'] = 4
sim.options['SARSA']['binCutoff'] = 0.5
sim.options['SARSA']['epsilonGreedy'] = 0.4
sim.options['SARSA']['useSupervisedTraining'] = False
sim.options['Sensor']['rayLength'] = 10
sim.options['Sensor']['numRays'] = 20
sim.options['Reward']['actionCost'] = 0.4
sim.options['Reward']['raycastCost'] = 40.0
# sim.options['Reward']['collisionPenalty'] = 200
sim.options['Car']['velocity'] = 16
sim.options['World']['obstaclesInnerFraction'] = 0.85
sim.options['dt'] = 0.05