Yuda Song

5

Papers

12

Total Citations

1

Affiliations

Affiliations

Carnegie Mellon University

Papers (5)

Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees

Accelerating Unbiased LLM Evaluation via Synthetic Feedback

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL

Hybrid Reinforcement Learning from Offline Observation Alone

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics