This thesis investigates the use of Bayesian analysis upon an opponent's behaviour in order to determine the desired goals or strategy used by a given adversary. A terrain analysis approach utilising the A* algorithm is investigated, where a probability distribution between discrete behaviours of an opponent relative to a set of possible goals is generated. The Bayesian analysis of agent behaviour accurately determines the intended goal of an opponent agent, even when the opponent's actions are altered randomly. The environment of Poker is introduced and abstracted for ease of analysis. Bayes' theorem is used to generate an effective opponent model, categorizing behaviour according to its similarity with known styles of opponent. The accuracy of Bayes' rule yields a notable improvement in the performance of an agent once an opponent's style is understood. A hybrid of the Bayesian style predictor and a neuroevolutionary approach is shown to lead to effective dynamic play, in comparison to agents that do not use an opponent model. The use of recurrence in evolved networks is also shown to improve the performance and generalizability of an agent in a multiplayer environment. These strategies are then employed in the full-scale environment of Texas Hold'em, where a betting round-based approach proves useful in determining and counteracting an opponent's play. It is shown that the use of opponent models, with the adaptive benefits of neuroevolution aid the performance of an agent, even when the behaviour of an opponent does not necessarily fit within the strict definitions of opponent 'style'.

This thesis investigates the use of Bayesian analysis upon an opponent¿s behaviour in order to determine the desired goals or strategy used by a given adversary. A terrain analysis approach utilising the A* algorithm is investigated, where a probability distribution between discrete behaviours of an opponent relative to a set of possible goals is generated. The Bayesian analysis of agent behaviour accurately determines the intended goal of an opponent agent, even when the opponent¿s actions are altered randomly. The environment of Poker is introduced and abstracted for ease of analysis. Bayes¿ theorem is used to generate an effective opponent model, categorizing behaviour according to its similarity with known styles of opponent. The accuracy of Bayes¿ rule yields a notable improvement in the performance of an agent once an opponent¿s style is understood. A hybrid of the Bayesian style predictor and a neuroevolutionary approach is shown to lead to effective dynamic play, in comparison to agents that do not use an opponent model. The use of recurrence in evolved networks is also shown to improve the performance and generalizability of an agent in a multiplayer environment. These strategies are then employed in the full-scale environment of Texas Hold¿em, where a betting round-based approach proves useful in determining and counteracting an opponent¿s play. It is shown that the use of opponent models, with the adaptive benefits of neuroevolution aid the performance of an agent, even when the behaviour of an opponent does not necessarily fit within the strict definitions of opponent ¿style¿. / Engineering and Physical Sciences Research Council (EPSRC)

Most story-based games today have manually-scripted non-player characters (NPCs) and the scripts are usually simple and repetitive since it is time-consuming for game developers to script each character individually. ScriptEase, a publicly-available author-oriented developer tool, attempts to solve this problem by generating script code from high-level design patterns, for BioWare Corp.'s role-playing game Neverwinter Nights. The ALeRT algorithm uses reinforcement learning (RL) to automatically generate NPC behaviours that change over time as the NPCs learn from the successes or failures of their own actions. This thesis aims to provide a new learning mechanism to game agents so they are capable of adapting to new behaviours based on the actions of other agents. The new on-line RL algorithm, ALeRT-AM, which includes an agent-modeling mechanism, is applied in a series of combat experiments in Neverwinter Nights and integrated into ScriptEase to produce adaptive behaviour patterns for NPCs.

No description available.

In Multi-Agenten-Systemen (MAS) kooperieren und konkurrieren Agenten um ihre jeweiligen Ziele zu erreichen. Für optimierte Agenten-Interaktionen sind Kenntnisse über die aktuellen und zukünftigen Handlungen anderer Agenten (Interaktionsparter, IP) hilfreich. Bei der Ermittlung und Nutzung solcher Kenntnisse kommt dem automatischen Erkennen und Verstehen sowie der Vorhersage von Verhalten der IP auf Basis von Beobachtungen besondere Bedeutung zu. Die Dissertation beschäftigt sich mit der automatischen Bestimmung und Vorhersage von Verhalten der IP durch einen Modellierenden Agenten (MA). Der MA generiert fallbasierte, adaptive Verhaltens-Modelle seiner IP und verwendet diese zur Vorhersage ihrer Verhalten. Als Anwendungsszenario wird mit dem virtuellen Fußballspiel des RoboCup ein komplexes und populäres MAS betrachtet. Der Hauptbeitrag dieser Arbeit besteht in der Ausarbeitung, Realisierung und Evaluierung eines Ansatzes zur automatischen Verhaltens-Modellierung für ein komplexes Multi-Agenten-System. / In multi-agent-systems agents cooperate and compete to reach their personal goals. For optimized agent interactions it is helpful for an agent to have knowledge about the current and future behavior of other agents. Ideally the recognition and prediction of behavior should be done automatically. This work addresses a way of automatically classifying and an attempt at predicting the behavior of a team of agents, based on external observation only. A set of conditions is used to distinguish behaviors and to partition the resulting behavior space. From observed behavior, team specific behavior models are then generated using Case Based Reasoning. These models, which are derived from a number of virtual soccer games (RoboCup), are used to predict the behavior of a team during a new game. The main contribution of this work is the design, realization and evaluation of an automatic behavior modeling approach for complex multi-agent systems.