We discuss two approaches for choosing a strategy in a two-player game. We suppose that the game is played a large number of rounds, which allows the players to use observations o...
Learning to converge to an efficient, i.e., Pareto-optimal Nash equilibrium of the repeated game is an open problem in multiagent learning. Our goal is to facilitate the learning ...
Internet advertising is a sophisticated game in which the many advertisers "play" to optimize their return on investment. There are many "targets" for the adve...
Abstract. A contract signing protocol lets two parties exchange digital signatures on a pre-agreed text. Optimistic contract signing protocols enable the signers to do so without i...
Rohit Chadha, John C. Mitchell, Andre Scedrov, Vit...
In the multi-armed bandit (MAB) problem there are k distributions associated with the rewards of playing each of k strategies (slot machine arms). The reward distributions are ini...