The Gift Exchange Game: Managing Opponent Actions

Interacting with an opponent is a fundamental concern in multiagent systems. In this work, we consider ways in which an agent can manipulate an opponent to adopt a preferred strategy. This difficult problem is often further complicated by the difficulty of analyzing the game. We have developed the Gift Exchange game, a sequential game that is deliberately simplified to focus on how to interact with an opponent. In this paper we describe the game and discuss different methods an agent might use to influence its opponent to select a preferred action. We show results from using simulated annealing to find optimal strategies to use against a learning opponent.