Solving Belief-Driven Pathfinding using Monte-Carlo Tree Search

Aversa Davide Vassos Stavros
2016 DiGRA/FDG '16 - Abstract Proceedings of the First International Joint Conference of DiGRA and FDG

In this work we discuss a stochastic extension to the (discrete) Belief-Driven Pathfinding (BDP) approach for finding personalized paths based on the beliefs of a character about the current state of the map. Our stochastic BDP upgrades previous work to the more realistic setting of using probabilities for the beliefs and takes advantage of approximate Monte Carlo Tree Search approaches.


Viewpoints AI: Procedurally Representing and Reasoning about Gestures

Jacob Mikhail Zook Alexander Magerko Brian
2014 DiGRA '13 - Proceedings of the 2013 DiGRA International Conference: DeFragging Game Studies

Viewpoints is a contemporary theatrical composition technique for understanding the expressive powers of gesture used to formally describe a dance performance or theatrical movement (Bogart 2005). We describe a computational system that integrates a gesture-based interface (Kinect), theatrical aesthetics framework (Viewpoints), AI reasoning architecture (Soar), and visualized embodiment of the AI participant (Processing) to explore novel forms of meaningful co-creative theatrical interaction in an interactive installation piece. Providing this ability to reason about a gesture’s meaning enables game designers to explore novel ways for players to communicate with intelligent game agents. Toward this end, we describe our prototype for live interaction with a projected virtual agent in an interactive installation piece.


Enhancing gameplay: challenges for articifical intelligence in digital games

Charles Darryl
2003 DiGRA '03 - Proceedings of the 2003 DiGRA International Conference: Level Up

Computer power in recent years has been advancing very rapidly and as increasingly more Artificial Intelligence (AI) experts turn their attention to game design, there is a clear opportunity to think more radically about digital game AI design. We suggest that not only is it timely for significant AI innovation but that it is essential to appreciably enhance key interactive aspects of digital game design, create opportunities for novel gameplay scenarios, and to progress the medium as an art form. Issues arising from the enhanced utilization of AI in digital games are discussed and the implications for gameplay explored; such as affecting player emotion, moral dilemmas, player created stories, dynamic and adaptive game worlds, and character believability.


Human, all too non-Human: Coop AI and the Conversation of Action

Simon Bart
2007 DiGRA '07 - Proceedings of the 2007 DiGRA International Conference: Situated Play

This paper considers the cultural sociological questions that might begin to be asked when players understand themselves to be cooperating rather than competing with the computer when they play digital games. Coop play with game AI in games like Call of Duty provides the basis for understanding human relationships with computers and machines in a way that may differ from the cultural historical antagonism embodied in a game like computer chess. This investigation also opens the doors for the analysis of emergent play in human-computer interaction.


A Procedural Critique of Deontological Reasoning

Togelius Julian
2011 DiGRA '11 - Proceedings of the 2011 DiGRA International Conference: Think Design Play

This paper describes a prototype game that learns its rules from the actions and commands of the player. This game can be seen as an implementation and procedural critique of Kant’s categorical imperative, suggesting to the player that (1) the maxim of an action is in general underdetermined by the action and its context, so that an external observer will more often than not get the underlying maxim wrong, and that (2) most ingame actions are morally “wrong” in the sense that they do not contribute to wellbalanced game design. But it can also be seen as an embryo for an authoring tool for game designers, where they can easily and fluidly prototype new game mechanics.


Beyond Adversarial: The Case for Game AI as Storytelling

Roberts David L. Riedl Mark O. Isbell Charles L.
2009 DiGRA '09 - Proceedings of the 2009 DiGRA International Conference: Breaking New Ground: Innovation in Games, Play, Practice and Theory

As a field, artificial intelligence (AI) has been applied to games for more than 50 years, beginning with traditional two-player adversarial games like tic-tac-toe and chess and extending to modern strategy games, first-person shooters, and social simulations. AI practitionershave become adept at designing algorithms that enable computers to play games at or beyond human levels in many cases. In this paper, we argue that the traditional goal of AI in games—to win the game—is not the only, nor the most interesting goal. An alternative goal for game AI is to make the human player’s play experience “better.”AI systems in games should reason about how to deliver the best possible experience within the context of the game. The key insight of this paper is that approaching AI reasoning for games as storytelling reasoning makes this goal much more attainable. We present an overview of traditional game AI techniques as well as a few more recentAI storytelling techniques. We also provide afoundation for describing and reasoning about games as stories, citing a number of examples. We conclude by discussingthe implications forfuture directions.