5 papers
Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
Yu Chen, Yuhao Liu, Jiatai Huang +2
We investigate episodic Markov Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity…
Provably Convergent Primal-Dual DPO for Constrained LLM Alignment
Yihan Du, Seo Taek Kong, R. Srikant
The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to pr…
Reinforcement Learning with Segment Feedback
Yihan Du, Anna Winnicki, Gal Dalal +2
Standard reinforcement learning (RL) assumes that an agent can observe a reward for each state-action pair. However, in practical applications, it is often difficult and costly to…
Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
Yihan Du, Anna Winnicki, Gal Dalal +2
Reinforcement Learning from Human Feedback (RLHF) has achieved impressive empirical successes while relying on a small amount of human feedback. However, there is limited theoretic…
Cascading Reinforcement Learning
Yihan Du, R. Srikant, Wei Chen
Cascading bandits have gained popularity in recent years due to their applicability to recommendation systems and online advertising. In the cascading bandit model, at each timeste…