ParallaxAI Alignment in Context

person

Jacob Makar-Limanov

Coauthor of STA-RLHF’s game-theoretic model of feedback training.

Jacob Makar-Limanov coauthored STA-RLHF: Stackelberg Aligned Reinforcement Learning with Human Feedback. The author-hosted manuscript lists Brown University’s computer-science affiliation and equal contributions by Makar-Limanov and Arjun Prakash.[1]

The paper connects his contribution here to leader–follower games and coupled preference-model training.

Sources

  1. STA-RLHF: Stackelberg Aligned Reinforcement Learning with Human Feedback · Source record src-041 · Back to claim ↑1

Pages that link here

Paper (1)

Article updated 2026-10-21