Hierarchical Solution of Markov Decision Processes using Macro-actions

TL;DR

This paper introduces a hierarchical approach to solving Markov decision processes using macro-actions only, significantly reducing state space and improving solution efficiency through an abstract MDP framework.

Contribution

Proposes a hierarchical model that exclusively uses macro-actions, creating an abstract MDP to efficiently approximate and solve original MDPs with reduced computational complexity.

Findings

Hierarchical macro-action model reduces state space size.

Abstract MDP provides efficient approximation of original MDP.

Macro-actions can be reused across related MDPs.

Abstract

We investigate the use of temporally abstract actions, or macro-actions, in the solution of Markov decision processes. Unlike current models that combine both primitive actions and macro-actions and leave the state space unchanged, we propose a hierarchical model (using an abstract MDP) that works with macro-actions only, and that significantly reduces the size of the state space. This is achieved by treating macroactions as local policies that act in certain regions of state space, and by restricting states in the abstract MDP to those at the boundaries of regions. The abstract MDP approximates the original and can be solved more efficiently. We discuss several ways in which macro-actions can be generated to ensure good solution quality. Finally, we consider ways in which macro-actions can be reused to solve multiple, related MDPs; and we show that this can justify the computational overhead of macro-action generation.