Round-based games are an instance of discrete planning problems. Some of the best contemporary game tree search algorithms use random roll-outs as data. Relying on a good policy, ...
We experimented a simple yet powerful optimization for Monte-Carlo Go tree search. It consists in dealing appropriately with strings that have two liberties. The heuristic is cont...
Opponent models are necessary in games where the game state is only partially known to the player, since the player must infer the state of the game based on the opponent’s acti...
Alan J. Lockett, Charles L. Chen, Risto Miikkulain...
Much of the work on opponent modeling for game tree search has been unsuccessful. In two-player, zero-sum games, the gains from opponent modeling are often outweighed by the cost ...
Nathan R. Sturtevant, Martin Zinkevich, Michael H....
In this paper we address the problem of coordination in multi-agent sequential decision problems with infinite statespaces. We adopt a game theoretic formalism to describe the int...