Author

Preston Fu

h-index 3 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching

It is shown that a simple and unbiased dense reward formulation, which is term progressive point matching, scales exponentially more efficiently to long-horizon tasks by rewarding partial progress on a segment level, both theoretically and empirically via synthetic environments.

Preston Fu, Kevin Frans, Oleh Rybkin et al. · 0 citations