30 search results - page 1 / 6 » A Polynomial-Time Algorithm for Action Graph Games |
AAAI
2006
14 years 17 days ago
2006
JGAA
2007
13 years 11 months ago
2007
Abstract. Two-player win-lose games have a simple directed graph representation. Exploiting this, we develop graph theoretic techniques for finding Nash equilibria in such games. ...
UAI
2004
14 years 16 days ago
2004
Action-graph games (AGGs) are a fully expressive game representation which can compactly express both strict and context-specific independence between players' utility functi...
IJCAI
2001
14 years 16 days ago
2001
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...
NIPS
2003
14 years 16 days ago
2003
We study how to learn to play a Pareto-optimal strict Nash equilibrium when there exist multiple equilibria and agents may have different preferences among the equilibria. We focu...