Workshop on Knowledge Extraction from Games (KEG 2019)

A Workshop at the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)

January 27/28, 2018

Honolulu, Hawaii, USA

Call for Papers

Knowledge Extraction from Games (KEG) is a workshop exploring questions of and approaches to the automated extraction of *knowledge* from games. We use “knowledge” in the broadest possible sense, including but not limited to design patterns or insights, game rules, character graphics, environment maps, music and sound effects, high-level goals, meaning or readings of the game, transferable skills, aesthetic standards and conventions, or abstracted models of games.

It includes and expands on the mandate of a recent vision paper at Computational Intelligence in Games (CIG 2017), Automated Game Design Learning.

Important Dates:

• November 12: Submissions due to organizers (via EasyChair)
• November 26: Notifications to authors
• December 8: Return camera-ready papers to organizers
• January 27/28: Workshop (Exact day TBD)

Games can be understood as simplified models of aspects of reality. They therefore provide useful structuring information for reasoning tasks and provide interesting environments for knowledge extraction and specification recovery--environments like video games, board games, and informal simulations of reality. For example, tasks like quadcopter control and stock market analysis can be understood as games.

Some examples of work that would be appropriate for KEG include:

• Contextual query-answering in games where non-player characters (or visual cues in environment design) offer hints to solve problems
• Extracting architectural information from game level layouts
• Transfer learning, analogical reasoning, or goal reasoning within or between games or game levels
• Game-playing agents which can explain their own actions or policy in terms of the game's rules
• Learning the rules of a game from observation, or learning higher-level rules or goals automatically
• Determining a designer or player's mental model of game rules, and whether that differs from the rules induced by the game's implementation

We also hope to include subject experts in game design and criticism; their deep knowledge of the creation and analysis of these highly emergent dynamical systems could inform knowledge representation and problem formulation.

KEG will accept a mix of two types of papers (references are not counted against page limits):

Full papers are 6-8 pages and are expected to be accompanied by some evaluation or formal proof.

Short papers are up to 4 pages, showing promising new directions, nascent ideas, or new applications of existing work.

We encourage authors to take whatever space they need, papers will be judged on the merit of their ideas, not length. All papers should be submitted to EasyChair in the AAAI format and will be subject to double-blind review (so, please take care to anonymize your submissions).

Given recent successes applying approaches from game studies in this area, we are especially keen to receive submissions from game designers or game critics on potentially mechanizable formalisms for knowledge representation and reasoning, either in the short paper category or as full papers (if accompanied, for example, by formal semantics or an evaluated implementation). We also welcome (especially in the short paper format) surveys or a reframing of existing work in related fields reoriented towards games.

We acknowledge the difficulty of attending these events in person. For those with personal, financial, or political inability for travel we are happy to organize remote presentations.

KEG 2018 is dedicated to a harassment-free workshop experience for everyone. Our anti-harassment policy can be found on our website.