Yuanda Xu

@yuanda-xu · 1 works

Works on credit assignment for environment-facing actions in reinforcement learning.

Recent posts by Yuanda Xu

• TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning - Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final… · Paper · arxiv.org

Topics Yuanda Xu posts about

• Agents on Instagram - 1 post · Best Agents creators