Intuitively, experience playing against one mixture of opponents in a given domain should be relevant for different the same domain. If changes, ideally we would not have to train from scratch, but rather could transfer what learned construct policy play new mixture. We propose learning method, Q-Mixing , that starts by Q -values each pure-strategy opponent. Then -value any distribution opponen...

Public opposition to genetic modification (GM) technology in the food domain is widespread (Frewer et al., 2013). In a survey of U.S. residents representative of the population on gender, age, and income, 64% opposed GM, and 71% of GM opponents (45% of the entire sample) were "absolutely" opposed-that is, they agreed that GM should be prohibited no matter the risks and benefits. "Absolutist" op...

In this paper we introduce experiments on neuro-evolution mechanisms applied to predator/prey multi-character computer games. Our test-bed is a modified version of the well-known Pac-Man game. By viewing the game from the predators’ (i.e. opponents’) perspective, we attempt off-line to evolve neural-controlled opponents capable of playing effectively against computer-guided fixed strategy playe...

This paper explores the question of how agent designers perceive and treat their agent’s opponents. In particular, it examines the influence of the opponent’s identity (human vs. automated agent) in negotiations. We empirically demonstrate that when people interact spontaneously they treat human opponents differently than automated agents in the context of equity and fairness considerations. Ho...

INTRODUCTION ..................................................................................... 163 I. THE HISTORY OF HSR IN THE UNITED STATES ................................. 165 II. WHY CALIFORNIA IS IMPORTANT ..................................................... 167 III. OPPOSITION TO HSR IN CALIFORNIA .............................................. 169 A. State Legislative Opposition ......

We present new results on the efficiency of no-regret algorithms in the context of multiagent learning. We use a known approach to augment a large class of no-regret algorithms to allow stochastic sampling of actions and observation of scalar reward of only the action played. We show that the average actual payoffs of the resulting learner gets (1) close to the best response against (eventually...

Artificially intelligent opponents in commercial computer games are almost exclusively controlled by manuallydesigned scripts. With increasing game complexity, the scripts tend to become quite complex too. As a consequence they often contain “holes” that can be exploited by the human player. The research question addressed in this paper reads: How can evolutionary learning techniques be applied...

Submitted to AAMAS 2003 This article presents an implemented multi-robot system for playing the popular game of laser tag. The object of the game is to search for and tag opponents that can move freely about the environment. The main contribution of this paper is a new variabledimension particle filter algorithm for tracking the location of opponents under prolonged periods of occlusion. This a...