Hedging Algorithms and Repeated Matrix Games
نویسندگان
چکیده
Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that UCB, M3, S or Exp3 algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on prediction problems. An hedging algorithm is made up with a top-level algorithm and a set of basic algorithms. To make its decision, an hedging algorithm uses its top-level algorithm to choose a basic algorithm, and the chosen algorithm makes the decision. This paper experimentally shows that well-selected hedging algorithms are better on average than all previous MAL algorithms on the task of playing RMG against various players. S is a very good top-level algorithm, and UCB and M3 are very good basic algorithms. Furthermore, two-level hedging algorithms are more effective than one-level hedging algorithms, and three levels are not better than two levels.
منابع مشابه
Multi-agent Learning Experiments on Repeated Matrix Games
This paper experimentally evaluates multiagent learning algorithms playing repeated matrix games to maximize their cumulative return. Previous works assessed that Qlearning surpassed Nash-based multi-agent learning algorithms. Based on all-againstall repeated matrix game tournaments, this paper updates the state of the art of multiagent learning experiments. In a first stage, it shows that M-Qu...
متن کاملJust add Pepper: extending learning algorithms for repeated matrix games to repeated Markov games
Learning in multi-agent settings has recently garnered much interest, the result of which has been the development of somewhat effective multi-agent learning (MAL) algorithms for repeated normal-form games. However, general-purpose MAL algorithms for richer environments, such as generalsum repeated stochastic (Markov) games (RSGs), are less advanced. Indeed, previously created MAL algorithms fo...
متن کاملUniversal Learning of Repeated Matrix Games
We study and compare the learning dynamics of two universal learning algorithms, one based on Bayesian learning and the other on prediction with expert advice. Both approaches have strong asymptotic performance guarantees. When confronted with the task of finding good long-term strategies in repeated 2× 2 matrix games, they behave quite differently.
متن کاملSequential Decision Problems
To this point in the class, we have studies stateless games when the payoff matrix is known. We have explored these games as both stage (single shot) games and as repeated games. In this portion of the class, we will continue to study repeated games, but we will assume as little about the problems as possible and we will look at a class of algorithms that allow us to represent states. To be pre...
متن کاملLearning to Teach and Follow in Repeated Games
The goal of an agent playing a repeated game is to maximize its payoffs over time. In repeated games between other learning agents, this often requires that an agent must learn to offer and accept profitable compromises. To do so, past research suggests that agents must implement both teaching and following strategies. However, few algorithms successfully employ both kinds of strategies simulta...
متن کامل