paper-with-me

Papers

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs

2025-04-16 · Kihyuk Hong, Ambuj Tewari

We study reinforcement learning in infinite-horizon average-reward settings with linear MDPs. Previous work addresses this problem by approximating the average-reward setting by discounted setting and employing a value iteration-based algorithm that uses clipping to constrain the span of the value function for improved statistical efficiency. However, the clipping procedure requires computing the minimum of the value function over the entire state space, which is prohibitive since the state space in linear MDP setting can be large or even infinite. In this paper, we introduce a value iteration method with efficient clipping operation that only requires computing the minimum of value functions over the set of states visited by the algorithm. Our algorithm enjoys the same regret bound as the previous work while being computationally efficient, with computational complexity that is independent of the size of the state space.

📄 PDF Abstract BibTeX arXiv:2504.11997

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

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

2024-05-23 · Kihyuk Hong, Woojin Chae, Yufan Zhang, Dabeen Lee 외

We study the infinite-horizon average-reward reinforcement learning with linear MDPs. Previous approaches either suffer from computational inefficiency or require strong assumptions on dynamics, such as ergodicity, for a…

Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

2020-07-23 · Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Rahul Jain

We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism principle and assuming that the MDP has a line…

Provably Efficient Infinite-Horizon Average-Reward Reinforcement Learning with Linear Function Approximation

2024-09-16 · Woojin Chae, Dabeen Lee

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear Markov decision processes (MDPs) and linear mixture MDPs under the Bellman optimality condition. While guarant…

Computational Efficiency

Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints

2022-01-31 · Liyu Chen, Rahul Jain, Haipeng Luo

We study regret minimization for infinite-horizon average-reward Markov Decision Processes (MDPs) under cost constraints. We start by designing a policy optimization algorithm with carefully designed action-value estimat…

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

2024-10-19 · Woojin Chae, Kihyuk Hong, Yufan Zhang, Ambuj Tewari 외

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 mixt…

parameter estimation