Ian Frank

Bio: Ian Frank is an academic researcher from Future University Hakodate. The author has contributed to research in topics: Game tree & Complete information. The author has an hindex of 13, co-authored 40 publications receiving 756 citations. Previous affiliations of Ian Frank include Vrije Universiteit Brussel & Future University in Egypt.

Football in Recent Times: What We Can Learn from the Newspapers

Abstract: This paper uses a basic statistical analysis of newspaper articles to gain an insight into the game of football. Basic features of the game axe established and examined in a way that should give insights to the designers of RoboCup teams and also suggest future developments for the regulations that determine the RoboCup environment. As concrete examples of possible Soccer Server modifications, we suggest touchline coaching, a revised model of stamina, and the inclusion of substitutions.

Optimal Play against Best Defence: Complexity and Heuristics

Abstract: We investigate the best defence model of an imperfect information game. In particular, we prove that finding optimal strategies for this model is NP-complete in the size of the game tree. We then introduce two new heuristics for this problem and show that they outperform previous algorithms. We demonstrate the practical use and effectiveness of these heuristics by testing them on random game trees and on a hard set of problems from the game of Bridge. For the Bridge problem set, our heuristics actually outperform the human experts who produced the model solutions.

Simulating inter-agent communication in disaster relief scenarios; an initial implementation of Rescue-MIKE

Abstract: Communication is a vital part of the teamwork that is required for disaster relief operations We have implemented a system, called Rescue-MIKE, which simulates the conversations that can be expected between large numbers of relief workers and controllers working in a rescue domain Our system uses multiple agents (director, continuity, background and monitors agents) to collect information from a simulated disaster scenario It then produces a dialogue that fits the actions of the agents in the domain We describe the implementation of our system, and also introduce walkie-talkie protocols that represent an initial formalisation of the conversation possibilities for this type of dialogue We discuss the likely applications of our system and protocols, which include knowledge elicitation about disaster relief control methods, automated relief support systems, and public education about the dangers of earthquakes

Trying to Understand RoboCup

Abstract: As the English striker Gary Lineker famously said, "Football is a very simple game. For 90 minutes, 22 men go running after the ball, and at the end, the Germans win." Although the game is simple, analyzing it can be hard. Just what makes one team better than another? How much difference do tactics make? Is there really such a thing as a "lucky win?" Here, we try to answer these questions in the context of RoboCup. We take the giant set of log data produced by the simulator tournaments from 1997 to 1999 and feed it to a data-munching program that produces statistics on important game features. Using these statistics, we identify precisely what has improved in RoboCup and what still requires further work. Plus, because the data muncher can work in real time, we can also release it as a proxy server for RoboCup. This proxy server gives all RoboCup developers instant access to statistics while a game is in progress and is a promising step toward an important goal: understanding RoboCup.

Dit4dah: predictive pruning for morse code text entry

Abstract: We present a new predictive pruning algorithm for text entry and show empirically how it outperforms simple text prediction. Our tests are based on a new application domain for predictive entry: the input of Morse code. Our motiviation for this work was to contribute to the development of efficient entry systems for the seriously disabled, but we found that the constraint of using a single key highlighted features of text prediction not previously closely scrutinised. In particular, our tests show how predictive text entry is affected by two factors: altering the rankings of completion candidates based on the difficulty of entering the remaining text with just the keyboard, and the number of candidates presented to the user.

Multiagent Systems: A Survey from a Machine Learning Perspective

Abstract: 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.

A Survey of Explanations in Recommender Systems

Abstract: 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.

Reinforcement learning for RoboCup soccer keepaway

Abstract: 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.

Heads-up limit hold’em poker is solved

Abstract: 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.