@inproceedings{WangBMP2011,
  title = {Balancing Safety and Exploitability in Opponent Modeling},
  booktitle = {Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2011)},
  abstract = {Opponent modeling is a critical mechanism in repeated games. It allows a player to adapt its strategy in order to better respond to the presumed preferences of his opponents. We introduce a new modeling technique that adaptively balances exploitability and risk reduction. An opponent’s strategy is modeled with a set of possible strategies that contain the actual strategy with a high probability. The algorithm is safe as the expected payoff is above the minimax payoff with a high probability, and can exploit the opponents’ preferences when sufficient observations have been obtained. We apply them to normal-form games and stochastic games with a finite number of stages. The performance of the proposed approach is first demonstrated on repeated rock-paper-scissors games. Subsequently, the approach is evaluated in a human-robot table-tennis setting where the robot player learns to prepare to return a served ball. By modeling the human players, the robot chooses a forehand, backhand or middle preparation pose before they serve. The learned strategies can exploit the opponent’s preferences, leading to a higher rate of successful returns.},
  pages = {1515-1520},
  editors = {Burgard, W. and Roth, D.},
  publisher = {AAAI Press},
  address = {Menlo Park, CA, USA},
  month = aug,
  year = {2011},
  slug = {wangbmp2011},
  author = {Wang, Z. and Boularias, A. and M{\"u}lling, K. and Peters, J.},
  month_numeric = {8}
}