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...
HEXQ is a reinforcement learning algorithm that discovers hierarchical structure automatically. The generated task hierarchy repthe problem at different levels of abstraction. In ...
Object-oriented applications are difficult to extend and maintain, due to the presence of implicit dependencies in the inheritance hierarchy. Although these dependencies often co...
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...
Computational models of grounded language learning have been based on the premise that words and concepts are learned simultaneously. Given the mounting cognitive evidence for conc...