Learning to play in digital games

Learning to play in digital games

There is growing interest in the use of games for educational purposes, particularly with regard to teaching curriculum subjects. Much of the research however has focused either on the content of games or the learning theory they illustrate. This paper presents a methodology that allows for an examination of how players learn to play. An understanding of this process is arguably crucial for inc...

Learning to Play Complex Games

We describe an algorithm, inspired by the biological behavior of ants, to efficiently determine intelligent moves and the genetic algorithm used to learn better strategies in a broad class of games. We present a class of games called Simple War Games that includes both deterministic and nondeterministic, perfect information, two-player, zero sum games. Simple War Games have a branching factor a...

Learning to Play Atari Games

Teaching computers to play video games is a complex learning problem that has recently seen increased attention. In this paper, we develop a system that, using constant model and hyperparameter settings, learns to play a variety of Atari games. In order to accomplish this task, we extract object features from the game screen, and provide these features as input into reinforcement learning algor...

Learning to play Bayesian games

This paper discusses the implications of learning theory for the analysis of games with a move by Nature. One goal is to illuminate the issues that arise when modeling situations where players are learning about the distribution of Nature’s move as well as learning about the opponents’ strategies. A second goal is to argue that quite restrictive assumptions are necessary to justify the concept ...

Learning to Play Network Games