Scalable Bilinear Pi Learning Using State and Action Features

ScalableBilinearπLearningUsingStateandActionFeaturesYichenChen1LihongLi2MengdiWang3Abstracte.g.,Azaretal.(2013)).Inotherwords,thereisanoraclethattakes(s,a)asinputandoutputsarandomswithprob-Approxi...