4 papers · 2 filters
Follow the Perturbed Leader for Linear Bandits: Regret over General Action Sets
Chen-Yu Wei
We give the first adversarial linear bandit algorithm based on Follow-the-Perturbed-Leader (FTPL) that achieves regret over general action sets. Our algorithm attains $\…
Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses
Jian Qian, Chen-Yu Wei
In adversarial multi-armed bandits, two performance measures are commonly used: static regret, which compares the learner to the best fixed arm, and dynamic regret, which compares…
On the Complexity of Offline Reinforcement Learning with -Approximation and Partial Coverage
Haolin Liu, Braham Snyder, Chen-Yu Wei
We study offline reinforcement learning under -approximation and partial coverage, a setting that motivates practical algorithms such as Conservative -Learning (CQL; Ku…
Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning
Haolin Liu, Dian Yu, Sidi Lu +6
Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs). However, most existing RL approaches rely…