Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks.

Chris Drummond Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks. 59-104 2002 16 J. Artif. Intell. Res. (JAIR) http://www.cs.washington.edu/research/jair/abstracts/drummond02a.html db/journals/jair/jair16.html#Drummond02