paper-with-me

Papers

Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process

2026-06-15 · Jongmin Lee, Ernest K. Ryu, Vaneet Aggarwal arxiv

While there is an extensive body of work characterizing the sample complexity of discounted cumulative-reward MDPs, finite sample analyses for average-reward MDPs have been limited, and most existing works rely on restrictive assumptions such as ergodicity or access to a generative model. In this work, we establish the first finite sample complexity guarantees from a single trajectory for weakly communicating average-reward MDPs. To this end, we study the dynamics of a single trajectory in weakly communicating MDPs and based on this analysis, we develop novel model-free methods. Notably, our value-based and policy-based methods provide finite sample complexity guarantees of $\widetilde{O}(1/\varepsilon^2)$ and $\widetilde{O}(1/\varepsilon^4)$ from a single trajectory in weakly communicating MDPs, respectively. Furthermore, we introduce the first model-free method that requires no prior knowledge of problem-dependent quantities for communicating MDPs.

📄 PDF Abstract BibTeX arXiv:2606.16729

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Ergodicity in reinforcement learning

2026-03-11 · Dominik Baumann, Erfaun Noorani, Arsenii Mustafin, Xinyi Sheng 외 arxiv

In reinforcement learning, we typically aim to optimize the expected value of the sum of rewards an agent collects over a trajectory. However, if the process generating these rewards is non-ergodic, the expected value, i…

Reinforcement Learning

Towards Optimal Offline Reinforcement Learning

2025-03-15 · Mengmeng Li, Daniel Kuhn, Tobias Sutter

We study offline reinforcement learning problems with a long-run average reward objective. The state-action pairs generated by any fixed behavioral policy thus follow a Markov chain, and the {\em empirical} state-action-…

reinforcement-learningReinforcement Learning

Efficient Solving of Large Single Input Superstate Decomposable Markovian Decision Process

2025-08-01 · Youssef Ait El Mahjoub, Jean-Michel Fourneau, Salma Alouah arxiv

Solving Markov Decision Processes (MDPs) remains a central challenge in sequential decision-making, especially when dealing with large state spaces and long-term optimization criteria. A key step in Bellman dynamic progr…

Batch Policy Learning in Average Reward Markov Decision Processes

2020-07-23 · Peng Liao, Zhengling Qi, Runzhe Wan, Predrag Klasnja 외

We consider the batch (off-line) policy learning problem in the infinite horizon Markov Decision Process. Motivated by mobile health applications, we focus on learning a policy that maximizes the long-term average reward…

A Duality Approach for Regret Minimization in Average-Award Ergodic Markov Decision Processes

2020-06-08 · L4DC 2020 6 · Hao Gong, Mengdi Wang

In light of the Bellman duality, we propose a novel value-policy gradient algorithm to explore and act in infinite-horizon Average-reward Markov Decision Process (AMDP) and show that it has sublinear regret. The algorith…