Deceptive Games
This work addresses the challenge of evaluating AI robustness in deceptive environments for game-playing algorithms, though it is incremental as it builds on existing frameworks and focuses on specific game types.
The authors tackled the problem of deceptive games, where reward structures mislead agents from optimal policies, by designing games in VGDL that exploit cognitive biases and testing them on AI agents in the GVGAI framework. Their results showed that all tested agents were vulnerable to deception, with different agents having specific weaknesses.
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.