ResearcharXivNEW

Planning Against Learning in Rank-1 Games

Overman 2026-08-18
William Overman

Learning algorithms are often used to make decisions in repeated multi-agent environments. When another player understands how a learner adapts from past experience, that player can plan strategically across rounds to influence the learner's future behavior. Recent work shows that optimizing against Replicator Dynamics, the continuous-time analogue of Multiplicative Weights Update, is tractable in

Read on arXiv
Data aggregated and editorially reviewed by TrendMing.

Key Contributions

  • Learning algorithms are often used to make decisions in repeated multi-agent environments.
  • When another player understands how a learner adapts from past experience, that player can plan strategically across rounds to influence the learner's future behavior.
  • Recent work shows that optimizing against Replicator Dynamics, the continuous-time analogue of Multiplicative Weights Update, is tractable in

Research Themes

AIResearch