Hierarchical Relative Entropy Policy Search

Many real-world problems are inherently hierarchically structured. The use of this structure in an agents policy may well be the key to improved scalability and higher performance on motor skill tasks. However, such hierarchical structures cannot be exploited by current policy search algorithms. We concentrate on a basic, but highly relevant hierarchy the `mixed option policy. Here, a gating network first decides which of the options to execute and, subsequently, the option-policy determines the action. Using a hierarchical setup for our learning method allows us to learn not only one solution to a problem but many. We base our algorithm on a recently proposed information theoretic policy search method, which addresses the exploitation-exploration trade-off by limiting the loss of information between policy updates.

Christian Daniel studied computational engineering at Technische Universitaet Darmstadt and EPFL Lausanne and is pursuing a PhD in Robot Learning. His research focuses on developing new learning algorithms for autonomous robots, especially in the field of robot skill learning and hierarchical reinforcement learning.