Name
Title | ||
|---|---|---|
General Self-Motivation and Strategy Identification: Case Studies Based on Sokoban and Pac-Man |
Abstract | ||
|---|---|---|
In this paper, we use empowerment, a recently introduced biologically inspired measure, to allow an AI player to assign utility values to potential future states within a previously unencountered game without requiring explicit specification of goal states. We further introduce strategic affinity, a method of grouping action sequences together to form “strategies,” by examining the overlap in the sets of potential future states following each such action sequence. We also demonstrate an information-theoretic method of predicting future utility. Combining these methods, we extend empowerment to soft-horizon empowerment which enables the player to select a repertoire of action sequences that aim to maintain anticipated utility. We show how this method provides a proto-heuristic for nonterminal states prior to specifying concrete game goals, and propose it as a principled candidate model for “intuitive” strategy selection, in line with other recent work on “self-motivated agent behavior.” We demonstrate that the technique, despite being generically defined independently of scenario, performs quite well in relatively disparate scenarios, such as a Sokoban-inspired box-pushing scenario and in a Pac-Man-inspired predator game, suggesting novel and principle-based candidate routes toward more general game-playing algorithms. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TCIAIG.2013.2295372 | Computational Intelligence and AI in Games, IEEE Transactions |
Keywords | Field | DocType |
artificial intelligence,computer games,information theory,AI player,Pac-Man-inspired predator game,Sokoban-inspired box-pushing scenario,anticipated utility,biologically inspired measure,concrete game goal,future utility,game-playing algorithm,information-theoretic method,intuitive strategy selection,nonterminal states,principle-based candidate,principled candidate model,self-motivated agent behavior,self-motivation,soft-horizon empowerment,strategic affinity,strategy identification,utility values,Artificial intelligence (AI),games,information theory | Information theory,Terminal and nonterminal symbols,Computer science,Repertoire,Software,Artificial intelligence,Sequential game,Machine learning,Empowerment | Journal |
Volume | Issue | ISSN |
6 | 1 | 1943-068X |
Citations | PageRank | References |
7 | 0.50 | 15 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Anthony, T. | 1 | 7 | 0.50 |
| Daniel Polani | 2 | 549 | 70.25 |
| Chrystopher L. Nehaniv | 3 | 48 | 7.30 |