Playing Large Games with Oracles and AI Debate

Xinyi Chen, Angelica Chen, Dean Foster, Elad Hazan

Keywords: regret minimization, AI Debate, large games

Abstract: We consider regret minimization in repeated games with a very large number of actions. Such games are inherent in the setting of AI safety via debate, and more generally games whose actions are language-based. Existing algorithms for online game playing require per-iteration computation polynomial in the number of actions, which can be prohibitive for large games. We thus consider oracle-based algorithms, as oracles naturally model access to AI agents. With oracle access, we characterize when internal and external regret can be minimized efficiently. We give a novel efficient algorithm for internal regret minimization whose regret depends logarithmically on the number of actions. We conclude with experiments in the setting of AI safety via debate that shows the benefit of insights from our algorithmic analysis.

Submission Number: 23