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...
Hierarchical topic taxonomies have proliferated on the World Wide Web [5, 18], and exploiting the output space decompositions they induce in automated classification systems is an...
Hierarchical Incremental Class Learning (HICL) is a new task decomposition method that addresses the pattern classification problem. HICL is proven to be a good classifier but clos...