Safe Exploitation of Predictions of Opponent Behavior

Given a prediction of opponent behavior in a general-sum two-player normal form game, it is difficult to select a strategy that balances the opportunity to use the prediction to inform one’s action with the risk of becoming predictable. We propose Restricted Stackelberg Response with Safety (RSRS), a novel way of generating such a strategy. RSRS uses an r-safe Stackelberg equilibrium in a modified game. We describe an algorithm which selects parameter values for RSRS to produce strategies that can play well against the prediction, respond to a best-responding opponent, or guard against worst-case outcomes. We have tested the algorithm on multiple general-sum games against different opponents.