Stefan J. Johansson

Using the Electric Field Approach in the RoboCup Domain

In autonomous robotics, so-called artificial potential fields are often used to plan and control the motion of a physical robot. In this paper, we propose to use an artificial electric field to address the problem or real time action selection in embodied, autonomous agents. We attach positive and negative electric charges to the relevant objects in the agents domain, and use the resulting electric field to estimate the heuristic value of a given configuration. This value is used to select the action that results in the best configuration. This allows us to consider in the same framework both navigation and manipulation actions. We apply the electric field approach in the RoboCup domain, and present results drawn from our experience in the Sony legged robots league.

On using multi-agent systems in playing board games

Computer programs able to play different kinds of games (aka bots) is a growing area of interest for the computer game industry as the demand for better skilled computerized opponents increase. We propose a general architecture of a Multi-agent System (Mas) based bot able to play complex board games and show that this solution is able to outperform other bots in two quite different games, namely no-press Diplomacy and Risk. Based on these results, we formulate a hypothesis of the applicability of Mas based bots in the domain of board games and identify the need for future investigations in the area.

A multiagent potential field-based bot for real-time strategy games

Bots for real-time strategy (RTS) games may be very challenging to implement. A bot controls a number of units that will have to navigate in a partially unknown environment, while at the same time avoid each other, search for enemies, and coordinate attacks to fight them down. Potential fields are a technique originating from the area of robotics where it is used in controlling the navigation of robots in dynamic environments. Although attempts have been made to transfer the technology to the gaming sector, assumed problems with efficiency and high costs for implementation have made the industry reluctant to adopt it. We present a multiagent potential field-based bot architecture that is evaluated in two different real-time strategy game settings and compare them, both in terms of performance, and in terms of softer attributes such as configurability with other state-of-the-art solutions. We show that the solution is a highly configurable bot that can match the performance standards of traditional RTS bots. Furthermore, we show that our approach deals with Fog of War (imperfect information about the opponent units) surprisingly well. We also show that a multiagent potential field-based bot is highly competitive in a resource gathering scenario.

Parrondo strategies for artificial traders

On markets with receding prices, artificial noise traders may consider alternatives to buy-and-hold. By simulating variations of the Parrondo strategy, using real data from the Swedish stock market, we produce first indications of a buy-low-sell-random Parrondo variation outperforming buy-and-hold. Subject to our assumptions, buy-low-sell-random also outperforms the traditional value and trend investor strategies. We measure the success of the Parrondo variations not only through their performance compared to other kinds of strategies, but also relative to varying levels of perfect information, received through messages within a multi-agent system of artificial traders.

The turing test track of the 2012 Mario AI Championship: Entries and evaluation

The Turing Test Track of the Mario AI Championship focused on developing human-like controllers for a clone of the popular game Super Mario Bros. Competitors participated by submitting AI agents that imitate human playing style. This paper presents the rules of the competition, the software used, the voting interface, the scoring procedure, the submitted controllers and the recent results of the competition for the year 2012. We also discuss what can be learnt from this competition in terms of believability in platform games. The discussion is supported by a statistical analysis of behavioural similarities and differences among the agents, and between agents and humans. The paper is co-authored by the organizers of the competition (the first three authors) and the competitors.

Dealing with fog of war in a Real Time Strategy game environment

Bots for real time strategy (RTS) games provide a rich challenge to implement. A bot controls a number of units that may have to navigate in a partially unknown environment, while at the same time search for enemies and coordinate attacks to fight them down. It is often the case that RTS AIs cheat in the sense that they get perfect information about the game world to improve the performance of the tactics and planning behavior. We show how a multi-agent potential field based bot can be modified to play an RTS game without cheating, i.e. with incomplete information, and still be able to perform well without spending more resources than its cheating version in a tournament.

Measuring player experience on runtime dynamic difficulty scaling in an RTS game

Do players find it more enjoyable to win, than to play even matches? We have made a study of what a number of players expressed after playing against computer opponents of different kinds in an RTS game. There were two static computer opponents, one that was easily beaten, and one that was hard to beat, and three dynamic ones that adapted their strength to that of the player. One of these three latter ones intentionally drops its performance in the end of the game to make it easy for the player to win. Our results indicate that the players found it more enjoyable to play an even game against an opponent that adapts to the performance of the player, than playing against an opponent with static difficulty. The results also show that when the computer player that dropped its performance to let the player win was the least enjoyable opponent of them all.

Characterization and evaluation of multi-agent system architectural styles

We argue that it is useful to study classes of Multi-Agent System (mas) architectures, corresponding to architectural styles in addition to particular architectures. In this work we focus on a particular abstraction level where mas architectural styles are characterized according to properties, such as, the type of control used (from fully centralized to fully distributed), and the type of coordination used. Different architectural styles support different quality attributes to different extent. When choosing architectural style for a given application domain, we argue that it is important to evaluate the them according to the quality attributes relevant to that application. The architectural style that provides the most appropriate balance between these attributes should then be selected. As a case study we investigate the problem of dynamic and distributed resource allocation and compare six mas architectural styles that can be used to handle this task. We also illustrate the use of the Analytic Hierarchy Process, which is a basic approach to select the most suitable alternative from a number of alternatives evaluated with respect to several criteria, for selecting the architectural style that balance the trade-off between the relevant quality attributes in the best way.

Tactical coordination in no-press diplomacy

While there is a broad theoretic foundation for creating computational players for two-player games, such as Chess, the multi-player domain is not as well explored. We make an attempt to apply a multi-agent approach to a multi-player game with huge search spaces and multiple adversaries, namely no-press Diplomacy. We tested our solution against other available bots in an open competition and show that our solution outperforms its competitors in score while being competitive in speed.

A study on human like characteristics in real time strategy games

Computer controlled characters (NPCs) are important in any video game to make the game world interesting, give more depth to a game and make the game playable. In almost any game the player has to cooperate with, fight against or interact with NPCs. This is especially true for single-player games but NPCs are also important in most multi-player games. When creating NPCs the developers often strive to create human like characters that behave reasonably intelligent in most cases. We have performed a study aiming to give an idea of the characteristics of human like NPCs in real-time strategy (RTS) games. In the study participants were asked to watch a recording of an RTS game and decide and motivate if the players in the game were controlled by a human player or a computer. We recorded matches were human players played against bots as well as bots playing against other bots. The results were categorized into different groups and they showed that some characteristics, for example simultaneous movement, are perceived as very bot-like and other things such as ability to try different tactics are perceived as humanlike.