Lookahead-Bounded Q-learning

Lookahead-BoundedQ-LearningIbrahimElShar1DanielR.Jiang1Abstractinthefollowingsense:writingthetransitiondynamicsasst+1=f(st,at,wt+1),wherestandatarethecurrentWeintroducetheLookahead-BoundedQ-learnin...