As the video game industry grows, both developers and creative authors seek new ways to simplify the process of controlling story content using scripts. This paper describes a story model and its software implementation, ScriptEase II, designed to solve this game design bottleneck. ScriptEase II is the second generation of the ScriptEase system, whose goal was to enable game authors with no programming ability to generate scripting code from high-level game patterns. ScriptEase II differs from the original in two important ways. First, ScriptEase II uses game-dependent translators to generate scripts for any game engine. Second, ScriptEase II uses a drag-and-drop interface that simplifies the story component creation menus that grew cumbersome in the original ScriptEase. The feasibility of code generation has been validated using three different game engines and the advantages of the simple drag-and-drop interface have been validated by a user study.

One of the major weaknesses of current real-time strategy (RTS) game agents is handling spatial reasoning at a high level. One challenge in developing spatial reasoning modules for RTS agents is to evaluate the ability of a given agent for this competency due to the inevitable confounding factors created by the complexity of these agents. We propose a simplified game that mimics spatial reasoning aspects of more complex games, while removing other complexities. Within this framework, we analyze the effectiveness of classical reinforcement learning for spatial management in order to build a detailed evaluative standard across a broad set of opponent strategies. We show that against a suite of opponents with fixed strategies, basic Q-learning is able to learn strategies to beat each. In addition, we demonstrate that performance against unseen strategies improves with prior training from other distinct strategies. We also test a modification of the basic algorithm to include multiple actors, to speed learning and increase scalability. Finally, we discuss the potential for knowledge transfer to more complex games with similar components.

In this paper we describe a method of modeling play styles as deviations from approximations of game theoretically rational actions. These deviations are interpreted as containing information about player skill and player decision making style. We hypothesize that this information is useful for differentiating between players and for understanding why human player behavior is attributed intentionality which we argue is a prerequisite for believability. To investigate these hypotheses we describe an experiment comparing 400 games in the Mario AI Benchmark testbed, played by humans, with equivalent games played by an approximately game theoretically rationally playing AI agent. The player actions’ deviations from the rational agent’s actions are subjected to feature extraction, and the resulting features are used to cluster play sessions into expressions of different play styles. We discuss how these styles differ, and how believable agent behavior might be approached by using these styles as an outset for a planning agent. Finally, we discuss the implications of making assumptions about rational game play and the problematic aspects of inferring player intentions from behavior.

Monte Carlo Tree Search (MCTS) has produced many recent breakthroughs in game AI research, particularly in computer Go. In this paper we consider how MCTS can be applied to create engaging AI for a popular commercial mobile phone game: Spades by AI Factory, which has been downloaded more than 2.5 million times. In particular, we show how MCTS can be integrated with knowledge-based methods to create an interesting, fun and strong player which makes far fewer plays that could be perceived by human observers as blunders than MCTS without the injection of knowledge. These blunders are particularly noticeable for Spades, where a human player must co-operate with an AI partner. MCTS gives objectively stronger play than the knowledge-based approach used in previous versions of the game and offers the flexibility to customise behaviour whilst maintaining a reusable core, with a reduced development cycle compared to purely knowledge-based techniques.

In this paper we explore the use of recursive cubic Hermite splines to mimic human movement in open world games. Human-like movement in an open world environment has many characteristics that are not optimal or directed towards clear, discrete goals. Using data collected from a simple MMORPG-like game, we use our spline representation to model human player movements relative to corresponding optimal paths. Using this representation, we show that simple distributions can be used to estimate control parameters to generate human-like movement across a population of agents in a novel environment.

Smart decision making at the tactical level is important for Artificial Intelligence (AI) agents to perform well in the domain of real-time strategy (RTS) games.  This paper presents a Bayesian model that can be used to predict the outcomes of isolated battles, as well as predict what units are needed to defeat a given army.  Model parameters are learned from simulated battles, in order to minimize the dependency on player skill.  We apply our model to the game of StarCraft,  with the end-goal of using the predictor as a module for making high-level combat decisions, and show that the model is capable of making accurate predictions.

In order to automatically generate high-quality game levels, one needs to be able to automatically verify that the levels are playable. The simulation-based approach to playability testing uses an artificial agent to play through the level, but building such an agent is not always an easy task and such an agent is not always readily available. We discuss this prob- lem in the context of the physics-based puzzle game Cut the Rope, which features continuous time and state space, mak- ing several approaches such as exhaustive search and reactive agents inefficient. We show that a deliberative Prolog-based agent can be used to suggest all sensible moves at each state, which allows us to restrict the search space so that depth-first search for solutions become viable. This agent is successfully used to test playability in Ropossum, a level generator based on grammatical evolution. The method proposed in this paper is likely to be useful for a large variety of games with similar characteristics.

Artificial intelligence (AI) techniques have been applied to video games to make the overall experience more enjoyable. In games with interactive storytelling (IS), player actions can substantially affect plot events and plot characters. Therefore, AI planning techniques have been used to shape the plot inresponse to player actions that conflict with authorial goals. While such methods are poised to increase player fun andagency, two recent implementations (ASD and PAST) have not been formally evaluated to date. In this paper we do so via a series of user studies for the first time. We show that ASD significantly enhances fun and agency, whereas PAST gets mixed results with an interaction between effects of the experience manager and player prior gaming experience in one user study, and marginally significant results for increased agency in a study with a constrained story domain.

Game tree search in games with large branching factors is a notoriously hard problem. In this paper, we address this problem with a new sampling strategy for Monte Carlo Tree Search (MCTS) algorithms, called "Naive Sampling", based on a variant of the Multi-armed Bandit problem called the "Combinatorial Multi-armed Bandit" (CMAB) problem. We present a new MCTS algorithm based on Naive Sampling called NaiveMCTS, and evaluate it in the context of real-time strategy (RTS) games. Our results show that as the branching factor grows, NaiveMCTS performs significantly better than other algorithms.

Designing adaptive games for individual emotional experiences is a tricky task, especially when detecting a player’s emotional state in real time requires physiological sensing hardware and signal processing software. There is currently a lack of software that can identify and learn how emotional states in games are triggered. To address this problem, we developed a system capable of understanding the fundamental relations between emotional responses and their eliciting events. We propose time-evolving Affective Reaction Models (ARM), which learn new affective reactions and manage conflicting ones. These models are then meant to provide information on how a set of predetermined game parameters (e.g., enemy and item spawning, music and lighting effects) should be adapted, to modulate the player’s emotional state. In this paper, we propose and describe a framework for modulating player emotions and the main components involved in regulating players’ affective experience. We expect our technique will allow game designers to focus on defining high-level rules for generating gameplay experiences instead of having to create and test different content for each player type.