Optimistic linear programming gives logarithmic regret for irreducible MDPs
Tewari, Ambuj & Bartlett, Peter L. (2008) Optimistic linear programming gives logarithmic regret for irreducible MDPs. In Platt, John, Koller, Daphne, Singer, Yoram, & Rowies, Sam (Eds.) Advances in Neural Information Processing Systems 20 (NIPS) , 2008, Cambridge, MA.
We present an algorithm called Optimistic Linear Programming (OLP) for learning to optimize average reward in an irreducible but otherwise unknown Markov decision process (MDP). OLP uses its experience so far to estimate the MDP. It chooses actions by optimistically maximizing estimated future rewards over a set of next-state transition probabilities that are close to the estimates, a computation that corresponds to solving linear programs. We show that the total expected reward obtained by OLP up to time T is within C(P) log T of the reward obtained by the optimal policy, where C(P) is an explicit, MDP-dependent constant. OLP is closely related to an algorithm proposed by Burnetas and Katehakis with four key differences: OLP is simpler, it does not require knowledge of the supports of transition probabilities, the proof of the regret bound is simpler, but our regret bound is a constant factor larger than the regret of their algorithm. OLP is also similar in flavor to an algorithm recently proposed by Auer and Ortner. But OLP is simpler and its regret bound has a better dependence on the size of the MDP.
Impact and interest:
Citation counts are sourced monthly from and citation databases.
These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Item Type:||Conference Paper|
|Additional Information:||A free full-text of the paper is available from the link above.|
|Keywords:||MDPs, Optimistic Linear Programming|
|Subjects:||Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > INFORMATION SYSTEMS (080600)|
|Divisions:||Past > QUT Faculties & Divisions > Faculty of Science and Technology
Past > Schools > Mathematical Sciences
|Deposited On:||01 Sep 2011 00:13|
|Last Modified:||01 Sep 2011 00:16|
Repository Staff Only: item control page