Adaptive strategies are popular in poker AI research. Three desirable properties of an adaptive poker bot are optimality, generality and speed of response to new opponents. These three properties though cannot be achieved simultaneously for most imperfect information games; some trade-off must be made between them. This general principle is connected to recent work on poker AI and particularly the total bankroll competitions at the Annual Computer Poker Competition (ACPC). This paper is meant to generate discussion between researchers about how to explain and quantify these trade-offs better and to possible future directions for research.
展开▼