All images at the end of the bibliography!
HQ-learning is a hierarchical extension of Q()-learning designed to solve certain types of partially observable Markov decision problems (POMDPs). HQ automatically decomposes POMDPs into sequences of simpler subtasks that can be solved by memoryless policies learnable by reactive subagents. HQ can solve partially observable mazes with more states than those used in most previous POMDP work.
Keywords: reinforcement learning, hierarchical Q-learning, POMDPs, non-Markov, subgoal learning.
Running head: HQ-Learning