Influence Maps have been successfully used in controlling the navigation of multiple units. In this paper, we apply the idea to the problem of simulating a kiting behavior (also known as ¨attack and flee'¨) in the context of real-time strategy (RTS) games. We present our approach and evaluate it in the popular RTS game StarCraft, where we analyze the benefits that our approach brings to a StarCraft playing bot.

We describe a heuristic search technique for multi-agent pursuit-evasion games in partially observable Euclidean space where a team of trackers attempt to minimize their uncertainty about an evasive target. Agents' movement and observation capabilities are restricted by polygonal obstacles, while each agent's knowledge of the other agents is limited to direct observation or periodic updates from team members. Our polynomial-time algorithm is able to generate strategies for games in continuous two-dimensional Euclidean space, an improvement over past algorithms that were only applicable to simple gridworld domains. We demonstrate that our algorithm is tolerant of interruptions in communication between agents, continuing to generate good strategies despite long periods of time where agents are unable to communicate directly. Experiments also show that our technique generates effective strategies quickly, with decision times of less than a second for reasonably sized domains with six or more agents.

Complex games such as RTS games are naturally formalized as Markov games. Given a Markov game, it is often possible to hand-code or learn a set of policies that capture the diversity of possible strategies. It is also often possible to hand-code or learn an abstract simulator of the game that can estimate the outcome of playing two strategies against one another from any state. We consider how to use such policy sets and simulators to make decisions in large Markov games. Prior work has considered the problem using an approach we call minimax policy switching. At each decision epoch, all policy pairs are simulated against each other from the current state, and the minimax policy is chosen and used to select actions until the next decision epoch. While intuitively appealing, we show that this switching policy can have arbitrarily poor worst case performance. In response, we describe a modified algorithm, monotone policy switching, whose worst case performance, under certain conditions, is provably no worse than the minimax fixed policy in the set. We evaluate these switching policies in both a simulated RTS game and the real game Wargus. The results show the effectiveness of policy switching when the simulator is accurate, and also highlight challenges in the face of inaccurate simulations.

This paper describes a gestural approach to interacting with interactive narrative characters that supports co-creativity. It describes our approach using a Microsoft Kinect to created a short scene with an intelligent avatar and an AI-controlled actor. It describes our preliminary user studies and a recommendation for future evaluation.

We address the problem of determining the structure of a set of plot points for an interactive narrative. To do so, we define a formal two-player game where a computer can play with an author to learn the structural representation of the story. This technique will allow for authors unfamiliar, or uncomfortable, with mathematical structures to create the inputs interactive narrative algorithms require. We include the underlying mathematical theory as a foundation of our approach, and characterize it's effectiveness through a series of simulation experiments. Results indicate there is promise in using formal games to aid in authoring interactive narrative structures.

My research is focused on using human navigation data ingames and simulation to learn motion models from trajectorydata. These motion models can be used to: 1) track the opponent’smovement during periods of network occlusion; 2)learn combat tactics by demonstration; 3) guide the planningprocess when the goal is to intercept the opponent. A trainingset of example motion trajectories is used to learn twotypes of parameterized models: 1) a second order dynamicalsteering model or 2) the reward vector for a Markov DecisionProcess. Candidate paths from the model serve as themotion model in a set of particle filters for predicting the opponent’slocation at different time horizons. Incorporating theproposed motion models into game bots allows them to customizestheir tactics for specific human players and functionas more capable teammates and adversaries.

The prevalence of virtual worlds presents an interesting The research questions we are looking to solve are: challenge for intelligent mobile agents. Online, very largescale, - How to represent maps of large scale, complex environments persistent virtual worlds such as Second Life (Linden Research Inc. 2012) and massively multi-player online games (MMOs) are becoming more popular. As these - How an agent can generate, update and use these maps worlds grow in size there is a challenge in providing intelligent - How can we utilise user-generated information to build agents that can generate and use maps of these environments and improve upon these maps without the need for hard-coding or pre-processing the map.

Serious games offer an opportunity for players to learn communication skills by practicing conversations with nonplaying characters (NPCs). To realize this potential, the player needs freedom of play to discover the relationships between its actions and their effects on the partner and the conversation. Scripting is currently the common approach to design in-game dialogue. Although scripting is a robust technique, the approach tends to produce deterministic conversations, allowing little control to the player. It is claimed that a Belief-Desire-Intention (BDI) approach to model the behavior of NPCs allows greater freedom to the player, and delivers better scalability and re-use of dialogues. This claim is evaluated by using BDI in the development of a sales-talk training game in the real-estate domain. It is concluded that BDI enables representative NPCs that respond appropriately and the game allows the player its freedom of choice to explore. The results also showed that BDI brings about new challenges to address, in order to further increase the quality of in-game dialogue.

Location-based games are an emerging paradigm fortraining, simulation, entertainment, health and many other domains. In this paper, we consider the role of artificialagents in such games. We also examine how human teams perform when given the same game, playedin both a real environment with mobile devices and alsoin a virtual environment that replicates the real environment.We perform the first direct comparison of real andvirtual instantiations of the same location-based game.We show the similarities and differences in game playand then investigate how adding an advice-giving agentchanges the experience.

However, due to the small numbers of goals present in existing systems, goal management Autonomous AI systems should be aware of their own goals is a relatively simple affair. Hanheide et al. (2010) describe and be capable of independently formulating behaviour to a system similar in architecture to our own that manages address them. We would ideally like to provide an agent with just two goals, whereas the one discussed in this paper must a collection of competences that allow it to act in novel situations manage upwards of forty. As the number of goals increases, that may not be predictable at design-time. In particular, the potential for goal conflict grows. This leads to a requirement we are interested in the operation of AI systems in for more sophisticated management processes, such as complex, oversubscribed domains where there may exist a dynamic goal re-prioritisation, allowing agents to alter their variety of ways to address high-level goals by composing behaviour to meet changing operational requirements. In the behaviours to achieve a set of sub-goals taken from a larger oversubscribed problem domains we are interested in, encoding set. Our research focusses how such sub-goals might be chosen all possible operating strategies at design time may (i.e.