We consider perfect-information reachability stochastic games for 2 players on infinite graphs. We identify a subclass of such games, and prove two interesting properties of it: first, Player Max always has optimal strategies in games from this subclass, and second, these games are strongly determined. The subclass is defined by the property that the set of all values can only have one accumula...

We study Recursive Concurrent Stochastic Games (RCSGs), extending our recent analysis of recursive simple stochastic games [14, 15] to a concurrent setting where the two players choose moves simultaneously and independently at each state. For multi-exit games, our earlier work already showed undecidability for basic questions like termination, thus we focus on the important case of single-exit ...

We consider a general class of nonzero-sum N-player stochastic games with impulse controls, where players control the underlying dynamics discrete interventions. adopt veri?cation approach and provide su?cient conditions for Nash equilibria (NEs) game. then limiting situation when N goes to in?nity, that is, suitable mean-?eld game (MFG) controls. show under appropriate technical conditions, th...

We examine n-player stochastic games. These are dynamic games where a play evolves in stages along a finite set of states; at each stage players independently have to choose actions in the present state and these choices determine a stage payoff to each player as well as a transition to a new state where actions have to be chosen at the next stage. For each player the infinite sequence of his s...

Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers. Current frameworks for stochastic games and reinforcement learning prohibit tuneable strategies as they seek optimal performance. In this paper, we enable such tuneable behaviour by generalising soft Q-learning...

Game theory (GT) is an essential formal tool for interacting entities; however computing equilibria in GT is a hard problem. When the same game can be played repeatedly over time, the problem becomes even more complicated. The existence of multiple game states makes the problem of computing equilibria in such games extremely difficult. In this paper, we approach this problem by first proposing ...

We deal with n-player AT stochastic games, where AT stands for additive transitions. These are stochastic games in which the transition probability vector ps(as), for action combination as 1⁄4 ðas ; . . . ; as Þ in state s, can be decomposed into player-dependent components as: 0377-2 doi:10. * Co E-m psðasÞ 1⁄4 Xn

We provide a computable algorithm to calculate uniform ε-optimal strategies in two-player zero-sum stochastic games. Our approach can be used to construct algorithms that calculate uniform ε-equilibria and uniform correlated ε-equilibria in various classes of multi-player non-zero-sum stochastic games. JEL codes: C63, C73.

We present a new algorithm for polynomial time learning of optimal behavior in single-controller stochastic games. This algorithm incorporates and integrates important recent results of Kearns and Singh 5] in reinforcement learning and of Monderer and Tennenholtz 7] in repeated games. In stochastic games, the agent must cope with the existence of an adversary whose actions can be arbitrary. In ...

This paper develops a theory of regular Markov perfect equilibria in dynamic stochastic games. We show that almost all dynamic stochastic games have a finite number of locally isolated Markov perfect equilibria that are all regular. These equilibria are essential and strongly stable. Moreover, they all admit purification. JEL classification numbers: C73, C61, C62.