← Search

Woojin Chae

2 accepted papers

2025

Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span

AISTATS 2025poster

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear mixture Markov decision processes (MDPs) under the Bellman optimality condition. Our algorithm for linear mixture MDPs achieves a nearly minimax optimal regret upper bound of $\widetilde{\ma…

Cited by 0SourceScholar
2025

Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs

AISTATS 2025poster

We study the problem of infinite-horizon average-reward reinforcement learning with linear Markov decision processes (MDPs). The associated Bellman operator of the problem not being a contraction makes the algorithm design challenging. Previous approaches either suffer from computational inefficienc…

Cited by 0SourceScholar