English
Related papers

Related papers: Non-stationary Reinforcement Learning under Genera…

200 papers

We consider model-free reinforcement learning (RL) in non-stationary Markov decision processes. Both the reward functions and the state transition functions are allowed to vary arbitrarily over time as long as their cumulative variations do…

Machine Learning · Computer Science 2022-08-23 Weichao Mao , Kaiqing Zhang , Ruihao Zhu , David Simchi-Levi , Tamer Başar

In this paper, we study policy evaluation in continuous-time reinforcement learning (RL), where the state follows an unknown stochastic differential equation (SDE), but only discrete-time data are available. We first highlight that the…

Optimization and Control · Mathematics 2026-02-23 Yuhua Zhu

We consider the regret minimization problem in reinforcement learning (RL) in the episodic setting. In many real-world RL environments, the state and action spaces are continuous or very large. Existing approaches establish regret…

Machine Learning · Computer Science 2022-06-29 Sayak Ray Chowdhury , Rafael Oliveira

Robust Markov Decision Processes (RMDPs) intend to ensure robustness with respect to changing or adversarial system behavior. In this framework, transitions are modeled as arbitrary elements of a known and properly structured uncertainty…

Machine Learning · Computer Science 2019-07-25 Esther Derman , Daniel Mankowitz , Timothy Mann , Shie Mannor

We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavior policy. We propose…

Machine Learning · Computer Science 2022-01-05 Yifei Min , Tianhao Wang , Dongruo Zhou , Quanquan Gu

Value function approximation is important in modern reinforcement learning (RL) problems especially when the state space is (infinitely) large. Despite the importance and wide applicability of value function approximation, its theoretical…

Machine Learning · Computer Science 2023-02-24 Hanlin Zhu , Ruosong Wang , Jason D. Lee

We initiate the study of dynamic regret minimization for goal-oriented reinforcement learning modeled by a non-stationary stochastic shortest path problem with changing cost and transition functions. We start by establishing a lower bound…

Machine Learning · Computer Science 2022-05-27 Liyu Chen , Haipeng Luo

Traditional reinforcement learning (RL) assumes the agents make decisions based on Markov decision processes (MDPs) with one-step transition models. In many real-world applications, such as energy management and stock investment, agents can…

Machine Learning · Computer Science 2025-10-22 Chenbei Lu , Zaiwei Chen , Tongxin Li , Chenye Wu , Adam Wierman

Discrete time stochastic optimal control problems and Markov decision processes (MDPs), respectively, serve as fundamental models for problems that involve sequential decision making under uncertainty and as such constitute the theoretical…

Optimization and Control · Mathematics 2023-03-08 Christian Beck , Arnulf Jentzen , Konrad Kleinberg , Thomas Kruse

Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on the robust average-reward MDPs under the model-free…

Machine Learning · Computer Science 2023-05-19 Yue Wang , Alvaro Velasquez , George Atia , Ashley Prater-Bennette , Shaofeng Zou

Reinforcement learning (RL) with linear function approximation has received increasing attention recently. However, existing work has focused on obtaining $\sqrt{T}$-type regret bound, where $T$ is the number of interactions with the MDP.…

Machine Learning · Computer Science 2021-02-19 Jiafan He , Dongruo Zhou , Quanquan Gu

We consider model selection for classic Reinforcement Learning (RL) environments -- Multi Armed Bandits (MABs) and Markov Decision Processes (MDPs) -- under general function approximations. In the model selection framework, we do not know…

Machine Learning · Statistics 2022-07-08 Avishek Ghosh , Sayak Ray Chowdhury

Policy design in non-stationary Markov Decision Processes (MDPs) is inherently challenging due to the complexities introduced by time-varying system transition and reward, which make it difficult for learners to determine the optimal…

Machine Learning · Computer Science 2025-11-17 Ziyi Zhang , Yorie Nakahira , Guannan Qu

We study decision making with structured observation (DMSO). Previous work (Foster et al., 2021b, 2023a) has characterized the complexity of DMSO via the decision-estimation coefficient (DEC), but left a gap between the regret upper and…

Machine Learning · Computer Science 2026-03-20 Haolin Liu , Chen-Yu Wei , Julian Zimmert

Real-world reinforcement learning is often \emph{nonstationary}: rewards and dynamics drift, accelerate, oscillate, and trigger abrupt switches in the optimal action. Existing theory often represents nonstationarity with coarse-scale models…

Machine Learning · Computer Science 2026-01-30 Zuyuan Zhang , Mahdi Imani , Tian Lan

We propose a novel algorithmic framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions. We derive several new algorithms for dynamic programming and…

We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations…

Machine Learning · Computer Science 2024-11-06 Long-Fei Li , Peng Zhao , Zhi-Hua Zhou

We present the first theoretical guarantees for differentially private online reinforcement learning (RL) with general function approximation, extending beyond prior work restricted to tabular and linear settings. Our approach combines a…

Machine Learning · Computer Science 2026-05-11 Yi He , Xingyu Zhou

We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value…

Machine Learning · Computer Science 2020-06-30 Andrea Zanette , Alessandro Lazaric , Mykel Kochenderfer , Emma Brunskill

We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it. We address this problem by extending the framework of robust MDPs to the…

Machine Learning · Computer Science 2017-11-10 Aurko Roy , Huan Xu , Sebastian Pokutta