HEXQ is a reinforcement learning algorithm that discovers hierarchical structure automatically. The generated task hierarchy repthe problem at different levels of abstraction. In ...
We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...
An open problem in reinforcement learning is discovering hierarchical structure. HEXQ, an algorithm which automatically attempts to decompose and solve a model-free factored MDP h...
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...
We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...