This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
Two notions of optimality have been explored in previous work on hierarchical reinforcement learning (HRL): hierarchical optimality, or the optimal policy in the space defined by ...
This paper presents the CQ algorithm which decomposes and solves a Markov Decision Process (MDP) by automatically generating a hierarchy of smaller MDPs using state variables. The ...
Abstract. Innovations such as optimistic exploration, function approximation, and hierarchical decomposition have helped scale reinforcement learning to more complex environments, ...