Sciweavers

ALDT
2009
Springer

Finding Best k Policies

14 years 6 months ago
Finding Best k Policies
Abstract. An optimal probabilistic-planning algorithm solves a problem, usually modeled by a Markov decision process, by finding its optimal policy. In this paper, we study the k best policies problem. The problem is to find the k best policies. The k best policies, k > 1, cannot be found directly using dynamic programming. Na¨ıvely, finding the k-th best policy can be Turing reduced to the optimal planning problem, but the number of problems queried in the na¨ıve algorithm is exponential in k. We show empirically that solving k best policy problem by using this reduction requires unreasonable amounts of time even when k = 3. We then provide a new algorithm, based on our theoretical contribution to prove that the k-th best policy differs from the i-th policy, for some i < k, on exactly one state. We show that the time complexity of the algorithm is quadratic in k, but the number of optimal planning problems it solves is linear in k. We demonstrate empirically that the new...
Peng Dai, Judy Goldsmith
Added 25 May 2010
Updated 25 May 2010
Type Conference
Year 2009
Where ALDT
Authors Peng Dai, Judy Goldsmith
Comments (0)