Two-Player Perfect-Information Shift-Invariant Submixing Stochastic Games Are Half-Positional
نویسندگان
چکیده
We consider zero-sum stochastic games with perfect information and finitely many states and actions. The payoff is computed by a function which associates to each infinite sequence of states and actions a real number. We prove that if the the payoff function is both shift-invariant and submixing, then the game is half-positional, i.e. the first player has an optimal strategy which is both deterministic and stationary. This result relies on the existence of ǫ-subgame-perfect strategies in shift-invariant games, a second contribution of the paper.
منابع مشابه
Algorithms for uniform optimal strategies in two-player zero-sum stochastic games with perfect information
In stochastic games with perfect information, in each state at most one player has more than one action available. We propose two algorithms which find the uniform optimal strategies for zero-sum two-player stochastic games with perfect information. Such strategies are optimal for the long term average criterion as well. We prove the convergence for one algorithm, which presents a higher comple...
متن کاملA Tool for the Direct Assessment of Poker Decisions
The element of luck permeates every aspect of the game of poker. Random stochastic outcomes introduce a large amount of noise that can make it very difficult to distinguish a good player from a bad one, much less trying to quantify small differences in skill. Good methods for directly assessing the quality of decisions exist for other stochastic games, including backgammon and blackjack. Howeve...
متن کاملPure and Stationary Optimal Strategies in Perfect-Information Stochastic Games
We consider two-players zero-sum perfect information stochastic games with finitely many states and actions and examine the problem of existence of pure stationary optimal strategies. We show that the existence of such strategies for one-player games (Markov decision processes) implies the existence of such strategies for two-player games. The result is general and holds for any payoff mapping.
متن کاملUsing counterfactual regret minimization to create competitive multiplayer poker agents
Games are used to evaluate and advance Multiagent and Artificial Intelligence techniques. Most of these games are deterministic with perfect information (e.g. Chess and Checkers). A deterministic game has no chance element and in a perfect information game, all information is visible to all players. However, many real-world scenarios with competing agents are stochastic (non-deterministic) with...
متن کاملPure and Stationary Optimal Strategies in Perfect-Information Stochastic Games with Global Preferences
We examine the problem of the existence of optimal deterministic stationary strategies in two-players antagonistic (zero-sum) perfect information stochastic games with finitely many states and actions. We show that the existence of such strategies follows from the existence of optimal deterministic stationary strategies for some derived one-player games. Thus we reduce the problem from two-play...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1401.6575 شماره
صفحات -
تاریخ انتشار 2014