Reproduce “Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling” on OpenResearch

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

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

About this paper

Abhijeet Sinha, Sundari Elango, Dianbo Liu

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