Learning Multidimensional Control Actions from Delayed Reinforcements

  • Pawea Cichosz
  • Published 1995


This paper addresses the problem of learning multidimensional control actions from delayed rewards. Classical reinforcement learning algorithms can be applied to tasks with multidimen-sional action spaces by recoding the action space appropriately (transforming it artiicially to a single dimension), but this straightforward recoding approach suuers from… (More)


  • Presentations referencing similar topics