Eecient Algorithms for Learning to Play Repeated Games against Computationally Bounded Adversaries
نویسندگان
چکیده
We study the problem of eeciently learning to play a game optimally against an unknown adversary chosen from a computationally bounded class. We both contribute to the line of research on playing games against nite automata, and expand the scope of this research by considering new classes of adversaries. We introduce the natural notions of games against recent history adversaries (whose current action is determined by some simple boolean formula on the recent history of play), and games against statistical adversaries (whose current action is determined by some simple function of the statistics of the entire history of play). In both cases we give eecient algorithms for learning to play penny-matching and a more diicult game called contract. We also give the most powerful positive result to date for learning to play against nite automata, an eecient algorithm for learning to play any game against any nite automata with probabilistic actions and low cover time.
منابع مشابه
4. Experimentation: the Effect of Exploration on the Agent's Performance
Model-based learning of interaction strategies in repeated-games has received a lot of attention in the game-theory literature. Gilboa & Samet [10] deal with bounded regular players. They describe a model-based learning strategy for repeated games that learns the best response against any regular strategy. Their procedure enumerates the set of all automata and chooses the current opponent model...
متن کاملEfficient Algorithms for Learning to Play Repeated Games Against Computationally Bounded Adversaries
In the game theory literature, there is an intriguing line of research on the problem of playing a repeated matrix game against an adversary whose computational resources are limited in some way. Perhaps the main way in which this research differs from classical game theory lies in the fact that when our adversary is not playing the minimax optimal strategy for the game, we may be able to attai...
متن کاملConvergence, Targeted Optimality, and Safety in Multiagent Learning
This paper introduces a novel multiagent learning algorithm, Convergence with Model Learning and Safety (or CMLeS in short), which achieves convergence, targeted optimality against memory-bounded adversaries, and safety, in arbitrary repeated games. The most novel aspect of CMLeS is the manner in which it guarantees (in a PAC sense) targeted optimality against memory-bounded adversaries, via ef...
متن کاملOnline Multiagent Learning against Memory Bounded Adversaries
The traditional agenda in Multiagent Learning (MAL) has been to develop learners that guarantee convergence to an equilibrium in self-play or that converge to playing the best response against an opponent using one of a fixed set of known targeted strategies. This paper introduces an algorithm called Learn or Exploit for Adversary Induced Markov Decision Process (LoE-AIM) that targets optimalit...
متن کاملLearning in real-time in repeated games using experts
Despite much progress, state-of-the-art learning algorithms for repeated games still often require thousands of moves to learn effectively – even in simple games. Our goal is to find algorithms that learn to play effective strategies in tens of moves in many games when paired against various associates. Toward this end, we describe a new meta-algorithm designed to increase the learning speed an...
متن کامل