Problem
Research questions and friction points this paper is trying to address.
Multiplicatively Optimistic
Regret Matching
General-sum Games
Full-information Self-play
Multiplicative Optimism for Constant Regret in Games
🤖 AI Summary
研究提出了一种名为MORM的学习规则，用于解决有限博弈中的遗憾问题，并通过单步乐观策略实现了所有时间范围内的常数遗憾。
📝 Abstract
We introduce Multiplicatively Optimistic Regret Matching (MORM), an uncoupled learning rule for finite general-sum games. Under simultaneous full-information self-play, every player achieves external regret $O(\sqrt n\log d)$ uniformly over all horizons, using only one-step optimism. The analysis combines a potential-based regret-matching argument with multiplicative stability and Hellinger control of strategy movement. A learning-rate safeguard additionally gives $O(\sqrt{T\log d})$ regret in the face of adversarial utilities.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multiplicatively Optimistic Regret Matching
one-step optimism
multiplicative stability
Hellinger control
🔎 Similar Papers
No similar papers found.
