Acceptable points in games of perfect information

Games with Perfect Information

Perfect-Information Stochastic Parity Games

We show that in perfect-information stochastic parity games with a finite state space both players have optimal pure positional strategies. Contrary to the recent proofs of this fact by K. Chatterejee, M. Jurdziński, T.A. Henzinger [2] and A.K. McIver, C.C. Morgan [14] the proof given in this paper proceeds by a straightforward induction on the number of outgoing transitions available to one of...

Perfect Information Stochastic Priority Games

We introduce stochastic priority games — a new class of perfect information stochastic games. These games can take two different, but equivalent, forms. In stopping priority games a play can be stopped by the environment after a finite number of stages, however, infinite plays are also possible. In discounted priority games only infinite plays are possible and the payoff is a linear combination...

Best-Response Cycles in Perfect Information Games

We consider n–player perfect information games with payoff functions having a finite image. We do not make any further assumptions, so in particular we refrain from making assumptions on the cardinality or the topology of the set of actions and assumptions like continuity or measurability of payoff functions. We show that there exists a best response cycle of length four, that is, a sequence (σ...

Reinforcement Learning in Perfect-Information Games∗

This paper studies action-based reinforcement learning in finite perfectioninformation games. Restrictions on the valuation updating rule that guarantee that the play eventually converges to a subgame-perfect Nash equilibrium (SPNE) are identified. These conditions are mild enough to contain interesting and plausible learning behavior. We provide two examples of such updating rule that suggest ...