Abstract—This paper presents a first attempt at evolving the rules for a game. In contrast to almost every other paper that applies computational intelligence techniques to games, we are not generating behaviours, strategies or environments for any particular game; we are starting without a game and generating the game itself. We explain the rationale for doing this and survey the theories of entertainment and curiosity that underly our fitness function, and present the details of a simple proofof-concept experiment.

Abstract not found

Abstract not found

Mainly motivated by the current lack of a qualitative and quantitative entertainment formulation of computer games and the procedures to generate it, this article covers the following issues: It presents the features—extracted primarily from the opponent behavior—that make a predator=prey game appealing; provides the qualitative and quantitative means for measuring player entertainment in real time, and introduces a successful methodology for obtaining games of high satisfaction. This methodology is based on online (during play) learning opponents who demonstrate cooperative action. By testing the game against humans, we confirm our hypothesis that the proposed entertainment measure is consistent with the judgment of human players. As far as learning in real time against human players is concerned, results suggest that longer games are required for humans to notice some sort of change in their entertainment.

In this article we propose a method that can deal with certain combinatorial reinforcement learning tasks. We demonstrate the approach in the popular Ms. Pac-Man game. We de ne a set of high-level observation and action modules, from which rule-based policies are constructed automatically. In these policies, actions are temporally extended, and may work concurrently. The policy of the agent is encoded by a compact decision list. The components of the list are selected from a large pool of rules, which can be either hand-crafted or generated automatically. A suitable selection of rules is learnt by the cross-entropy method, a recent global optimization algorithm that ts our framework smoothly. Crossentropy-optimized policies perform better than our hand-crafted policy, and reach the score of average human players. We argue that learning is successful mainly because (i) policies may apply concurrent actions and thus the policy space is su ciently rich, (ii) the search is biased towards low-complexity policies and therefore, solutions with a compact description can be found quickly if they exist. 1.

Abstract — We introduce a new reinforcement learning benchmark

Video games provide an opportunity and challenge for the soft computational intelligence methods like the symbolic games did for “good old-fashioned artificial intelligence. ” This article reviews the achievements and future prospects of one particular approach, that of evolving neural networks, or neuroevolution. This approach can be used to construct adaptive characters in existing video games, and it can serve as a foundation for a new genre of games based on machine learning. Evolution can be guided by human knowledge, allowing the designer to control the kinds of solutions that emerge and encouraging behaviors that appear visibly intelligent to the human player. Such techniques may allow building video games that are more engaging and entertaining than current games, and those that can serve as training environments for people. Techniques developed in these games may also be widely applicable in other fields, such as robotics, resource optimization, and intelligent assistants. 1

Abstract. This chapter surveys the research of us and others into applying evolutionary algorithms and other forms of computational intelligence to various aspects of racing games. We first discuss the various roles of computational intelligence in games, and then go on to describe the evolution of different types of car controllers, modelling of players ’ driving styles, evolution of racing tracks, comparisons of evolution with other forms of reinforcement learning, and modelling and controlling physical cars. It is suggested that computational intelligence can be used in different but complementary ways in racing games, and that there is unrealised potential for cross-fertilisation between research in evolutionary robotics and CI for games. 1 On the Roles of Computational Intelligence in Computer Games Computational Intelligence (henceforth “CI”) is the study of a diverse collection of algorithms and techniques for learning and optimisation that are somehow inspired by nature. Here we find evolutionary computation, which uses Darwinian survival of the fittest for solving problems, neural networks,

Abstract — Pac-Man (and variant) computer games have received some recent attention in Artificial Intelligence research. One reason is that the game provides a platform that is both simple enough to conduct experimental research and complex enough to require non-trivial strategies for successful gameplay. This paper describes an approach to developing Pac-Man playing agents that learn game-play based on minimal onscreen information. The agents are based on evolving neural network controllers using a simple evolutionary algorithm. The results show that neuroevolution is able to produce agents that display novice playing ability, with a minimal amount of onscreen information, no knowledge of the rules of the game and a minimally informative fitness function. The limitations of the approach are also discussed, together with possible directions for extending the work towards producing better Pac-Man playing agents.

Abstract — Applying neural networks to generate robust agent controllers is now a seasoned practice, with time needed only to isolate particulars of domain and execution. However we are often constrained to local problems due to an agents inability to reason in an abstract manner. While there are suitable approaches for abstract reasoning and search, there is often the issues that arise in using offline processes in real-time situations. In this paper we explore the feasibility of creating a decentralised architecture that combines these approaches. The approach in this paper explores utilising a classical automated planner that interfaces with a library of neural network actuators through the use of a Prolog rule base. We explore the validity of solving a variety of goals with and without additional hostile entities as well as added uncertainty in the the world. The end results providing a goal-driven agent that adapts to situations and reacts accordingly. I.