Tag
This paper presents an algorithm for group distributionally robust least squares regression using block Lewis weights, achieving improved complexity over interior point methods. It also provides interpolating algorithms between average and robust losses.
Introduces PROWL, a prioritized regret-driven optimization framework that uses an adversarial curriculum to improve diffusion-based world model robustness by focusing on high-error trajectories, achieving better performance on out-of-distribution scenarios in MineRL.
Introduces ODRPO, a framework that decomposes discrete rewards into ordinal binary indicators to improve robustness of policy optimization in RLAIF for LLMs, achieving up to 14.8% relative improvement with minimal overhead.
This paper introduces RQIQN, a robust quantile-based method for distributional reinforcement learning that uses Wasserstein geometry regularization to prevent distribution degeneration and improve performance in risk-sensitive tasks.