OpenResearch

Reproduce “Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Download for macOS

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Joery Ariën de Vries, Neil David Lawrence, Zhenwen Dai

Read on alphaXiv

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.