Deceptive games

Anderson, Damien and Stephenson, Matthew and Togelius, Julian and Salge, Christian and Levine, John and Renz, Jochen (2018) Deceptive games. Lecture Notes in Computer Science, 10784. pp. 376-391. ISSN 0302-9743 (https://doi.org/10.1007/978-3-319-77538-8_26)

[thumbnail of Anderson-etal-LNCS-2018-Deceptive-games]
Preview
 Text. Filename: Anderson_etal_LNCS_2018_Deceptive_games.pdf
Accepted Author Manuscript
Download (801kB)| Preview

Abstract

Deceptive games are games where the reward structure or other aspects of the game are designed to lead the agent away from a globally optimal policy. While many games are already deceptive to some extent, we designed a series of games in the Video Game Description Language (VGDL) implementing specific types of deception, classified by the cognitive biases they exploit. VGDL games can be run in the General Video Game Artificial Intelligence (GVGAI) Framework, making it possible to test a variety of existing AI agents that have been submitted to the GVGAI Competition on these deceptive games. Our results show that all tested agents are vulnerable to several kinds of deception, but that different agents have different weaknesses. This suggests that we can use deception to understand the capabilities of a game-playing algorithm, and game-playing algorithms to characterize the deception displayed by a game.

ORCID iDs

Anderson, Damien ORCID logoORCID: https://orcid.org/0000-0002-8554-3068, Stephenson, Matthew, Togelius, Julian, Salge, Christian, Levine, John ORCID logoORCID: https://orcid.org/0000-0001-7016-2978 and Renz, Jochen;
CORE (COnnecting REpositories)