Stochastic Games with Finite State and Action Spaces.
نویسندگان
چکیده
منابع مشابه
Stationary Nash Equilibria for Average Stochastic Games with Finite State and Action Spaces
Abstract. We study the problem of the existence of stationary Nash equilibria in infinite n-person stochastic games with limiting average payoff criteria for the players. The state and action spaces in the games are assumed to be finite. We present some results for the existence of stationary Nash equilibria in a multichain average stochastic game with n players. Based on constructive proof of ...
متن کاملMulitagent Reinforcement Learning in Stochastic Games with Continuous Action Spaces
We investigate the learning problem in stochastic games with continuous action spaces. We focus on repeated normal form games, and discuss issues in modelling mixed strategies and adapting learning algorithms in finite-action games to the continuous-action domain. We applied variable resolution techniques to two simple multi-agent reinforcement learning algorithms PHC and MinimaxQ. Preliminary ...
متن کاملSolving Stochastic Planning Problems with Large State and Action Spaces
Planning methods for deterministic planning problems traditionally exploit factored representations to encode the dynamics of problems in terms of a set of parameters, e.g., the location of a robot or the status of a piece of equipment. Factored representations achieve economy of representation by taking advantage of structure in the form of dependency relationships among these parameters. In r...
متن کاملO n the existence of equilibria to Bayesian games with non - finite type and action spaces *
Equilibria are shown to exist in non-finite Bayesian games if the type and action spaces are compact and convex subsets of finite dimensional Euclidean space, utility functions are continuous, expected utility functions are strictly quasiconcave in the agent’s action, the set of rationalizable mappings have a uniformly bounded slope and posterior beliefs are suitably continuous. 2002 Elsevier...
متن کاملImproving Performance in Imperfect-Information Games with Large State and Action Spaces by Solving Endgames
Sequential games of perfect information can be solved by backward induction, where solutions to endgames are propagated up the game tree. However, this does not work in imperfect-information games because different endgames can contain states that belong to the same information set and cannot be treated independently. In fact, we show that this approach can fail even in a simple game with a uni...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Journal of the Operational Research Society
سال: 1988
ISSN: 0160-5682
DOI: 10.2307/2582869