Deceptive games

Damien Anderson, Matthew Stephenson, Julian Togelius, Christian Salge, John Levine, Jochen Renz

Research output: Contribution to journalConference Contribution

8 Citations (Scopus)
14 Downloads (Pure)

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.
Original languageEnglish
Pages (from-to)376-391
Number of pages16
JournalLecture Notes in Computer Science
Volume10784
Early online date8 Mar 2018
DOIs
Publication statusE-pub ahead of print - 8 Mar 2018

    Fingerprint

Keywords

  • games
  • tree search
  • reinforcement learning
  • deception

Cite this

Anderson, D., Stephenson, M., Togelius, J., Salge, C., Levine, J., & Renz, J. (2018). Deceptive games. Lecture Notes in Computer Science, 10784, 376-391. https://doi.org/10.1007/978-3-319-77538-8_26