Sciweavers

AAAI
2010

Representation Discovery in Sequential Decision Making

13 years 10 months ago
Representation Discovery in Sequential Decision Making
Automatically constructing novel representations of tasks from analysis of state spaces is a longstanding fundamental challenge in AI. I review recent progress on this problem for sequential decision making tasks modeled as Markov decision processes. Specifically, I discuss three classes of representation discovery problems: finding functional, state, and abstractions. I describe solution techniques varying along several dimensions: diagonalization or dilation methods using approximate or exact transition models; rewardspecific vs reward-invariant methods; global vs. local representation construction methods; multiscale vs. flat discovery methods; and finally, orthogonal vs. redundant representation discovery methods. I conclude by describing a number of open problems for future work.
Sridhar Mahadevan
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2010
Where AAAI
Authors Sridhar Mahadevan
Comments (0)