Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a domain. Traditionally, DAI has been divided into two sub-disciplines: Distributed Problem Solving (DPS) focuses on the information management aspects of systems with several components working together towards a common goals Multiagent Systems (MAS) deals with behavior management in collections of several independent entities, or agents. This survey of MAS is intended to serve as an introduction to the field and as an organizational framework. A series of general multiagent scenarios are presented. For each scenario, the issues that arise are described along with a sampling of the techniques that exist to deal with them. The presented techniques are not exhaustive, but they highlight how multiagent systems can be and have been used to build complex systems. When options exist, the techniques presented are biased towards machine learning approaches. Additional opportunities for applying machine learning to MAS are highlighted and robotic soccer is presented as an appropriate test bed for MAS. This survey does not focus exclusively on robotic systems. However, we believe that much of the prior research in non-robotic MAS is relevant to robotic MAS, and we explicitly discuss several robotic MAS, including all of those presented in this issue.

/pdf/multiagent-systems-a-survey-from-a-machine-learning-yps633tity.pdf

Multiagent Systems: A Survey from a Machine Learning Perspective

This paper provides a comprehensive review of explanations in recommender systems. We highlight seven possible advantages of an explanation facility, and describe how existing measures can be used to evaluate the quality of explanations. Since explanations are not independent of the recommendation process, we consider how the ways recommendations are presented may affect explanations. Next, we look at different ways of interacting with explanations. The paper is illustrated with examples of explanations throughout, where possible from existing applications.

A Survey of Explanations in Recommender Systems

RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple independent agents learning simultaneously, and long and variable delays in the effects of actions. We describe our application of episodic SMDP Sarsa(λ) with linear tile-coding function approximation and variable λ to learning higher-level decisions in a keepaway subtask of RoboCup soccer. In keepaway, one team, “the keepers,” tries to keep control of the ball for as long as possible despite the efforts of “the takers.” The keepers learn individually when to hold the ball and when to pass to a teammate. Our agents learned policies that significantly outperform a range of benchmark policies. We demonstrate the generality of our approach by applying it to a number of task variations including different field sizes and different numbers of players on each team.

/pdf/reinforcement-learning-for-robocup-soccer-keepaway-ku565uhymb.pdf

Reinforcement learning for RoboCup soccer keepaway

Games and Decisions: Introduction and Critical Survey.

Poker is a family of games that exhibit imperfect information, where players do not have full knowledge of past events. Whereas many perfect-information games have been solved (e.g., Connect Four and checkers), no nontrivial imperfect-information game played competitively by humans has previously been solved. Here, we announce that heads-up limit Texas hold’em is now essentially weakly solved. Furthermore, this computation formally proves the common wisdom that the dealer in the game holds a substantial advantage. This result was enabled by a new algorithm, CFR + , which is capable of solving extensive-form games orders of magnitude larger than previously possible.

/pdf/heads-up-limit-hold-em-poker-is-solved-134wqlsfvm.pdf

Heads-up limit hold’em poker is solved

This article describes Soccer Server, a simulator of the game of soccer designed as a benchmark for evaluating multiagent systems and cooperative algorithms. In real life, successful soccer teams require many qualities, such as basic ball control skills, the ability to carry out strategies, and teamwork. We believe that simulating such behaviors is a significant challenge for computer science, artificial intelligence, and robotics technologies. It is to promote the development of such technologies, and to help define a new standard problem for research, that we have developed Soccer Server. We demonstrate the potential of Soccer Server by reporting an experiment that uses the system to compare the performance of a neural network architecture and a decision tree algorithm at learning the selection of soccer play plans. Other researchers using Soccer Server to investigate the nature of cooperative behavior in a multiagent environment will have the chance to assess their progress at RoboCup-97, an internatio...

Soccer server: A tool for research on multiagent systems

Search in games with incomplete information: a case study using Bridge card play

This paper describes MIKE, an automatic commentary system for the game of soccer. Since soccer is played by teams, describing the course of a game calls for reasoning about multi-agent interactions. Also, events may occur at any point of the field at any time, making it difficult to fix viewpoints. MIKE interprets this domain with six soccer analysis modules that run concurrently within a role-sharing framework. We describe these analysis modules and also discuss how to control the interaction between them so that an explanation of a game emerges reactively from the system. We present and evaluate examples of the match commentaries produced by MIKE in English, Japanese and French.

MIKE: an automatic commentary system for soccer

INTRODUCTION A kitchen is not just a place of labor. Throughout history, the activity of preparing food has been accompanied (and even used as an excuse for) social interaction and the development of social bonds. Modern lifestyles and convenience foods have reduced the time and effort required for cooking, but at the same time, have lessened the opportunities for interaction. Our contribution is to demonstrate how a “Kitchen of the Future” can use technology to re-introduce such social interactions, and also enable entirely novel forms of communication mediated by computer. Our kitchen supports the automatic generation of web-ready recipe pages, with other possible applications including actual cooking assistance, and communication or education across distances, cultures and generations.

Making recipes in the kitchen of the future

We examine three heuristic algorithms for games with imperfect information: Monte-carlo sampling, and two new algorithms we call vector minimaxing and payoff-reduction minimaxing. We compare these algorithms theoretically and experimentally, using both simple game trees and a large database of problems from the game of Bridge. Our experiments show that the new algorithms both out-perform Monte-carlo sampling, with the superiority of payoff-reduction minimaxing being especially marked. On the Bridge problem set, for example, Monte-carlo sampling only solves 66% of the problems, whereas payoff-reduction minimaxing solves over 95%. This level of performance was even good enough to allow us to discover five errors in the expert text used to generate the test database.

/pdf/finding-optimal-strategies-for-imperfect-information-games-1jfxqp1ssf.pdf

Ian Frank

Papers

Soccer server: A tool for research on multiagent systems

Search in games with incomplete information: a case study using Bridge card play

MIKE: an automatic commentary system for soccer

Making recipes in the kitchen of the future

Finding optimal strategies for imperfect information games