English
Related papers

Related papers: Q-Learning with Shift-Aware Upper Confidence Bound…

200 papers

We study learning in periodic Markov Decision Process (MDP), a special type of non-stationary MDP where both the state transition probabilities and reward functions vary periodically, under the average reward maximization setting. We…

Machine Learning · Computer Science 2023-03-20 Ayush Aniket , Arpan Chattopadhyay

Distributionally robust reinforcement learning (DRRL) focuses on designing policies that achieve good performance under model uncertainties. The goal is to maximize the worst-case long-term discounted reward, where the data for RL comes…

Machine Learning · Computer Science 2026-03-17 Saptarshi Mandal , Yashaswini Murthy , R. Srikant

This paper investigates the challenges of optimal online policy learning under missing data. State-of-the-art algorithms implicitly assume that rewards are always observable. I show that when rewards are missing at random, the Upper…

Econometrics · Economics 2025-07-29 Filippo Palomba

To address the needs of modeling uncertainty in sensitive machine learning applications, the setup of distributionally robust optimization (DRO) seeks good performance uniformly across a variety of tasks. The recent multi-distribution…

Machine Learning · Statistics 2026-01-01 Rafael Hanashiro , Patrick Jaillet

Time-inhomogeneous finite-horizon Markov decision processes (MDP) are frequently employed to model decision-making in dynamic treatment regimes and other statistical reinforcement learning (RL) scenarios. These fields, especially healthcare…

Machine Learning · Computer Science 2025-10-21 Elynn Chen , Sai Li , Michael I. Jordan

We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algorithm for reinforcement learning in tabular and possibly stage-dependent, episodic Markov decision process. UCBMQ is based on Q-learning where we add a momentum term…

Machine Learning · Statistics 2022-03-21 Pierre Menard , Omar Darwiche Domingues , Xuedong Shang , Michal Valko

Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes…

Machine Learning · Computer Science 2021-05-21 Lucas N. Alegre , Ana L. C. Bazzan , Bruno C. da Silva

By leveraging the representation power of deep neural networks, neural upper confidence bound (UCB) algorithms have shown success in contextual bandits. To further balance the exploration and exploitation, we propose…

Machine Learning · Computer Science 2025-03-12 Ha Manh Bui , Enrique Mallada , Anqi Liu

We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs). Both the reward functions and the state transition kernels are unknown and allowed to vary…

Machine Learning · Computer Science 2022-11-22 Yuhao Ding , Ming Jin , Javad Lavaei

We study off-dynamics Reinforcement Learning (RL), where the policy training and deployment environments are different. To deal with this environmental perturbation, we focus on learning policies robust to uncertainties in transition…

Machine Learning · Computer Science 2024-10-01 Zhishuai Liu , Weixin Wang , Pan Xu

We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain…

Machine Learning · Statistics 2025-10-09 Haochen Zhang , Zhong Zheng , Lingzhou Xue

We consider the problem of learning in a non-stationary reinforcement learning (RL) environment, where the setting can be fully described by a piecewise stationary discrete-time Markov decision process (MDP). We introduce a variant of the…

Machine Learning · Computer Science 2023-04-04 Reda Alami , Mohammed Mahfoud , Eric Moulines

Safe deployment of graph neural networks (GNNs) under distribution shift requires models to provide accurate confidence indicators (CI). However, while it is well-known in computer vision that CI quality diminishes under distribution shift,…

Machine Learning · Computer Science 2023-09-21 Puja Trivedi , Mark Heimann , Rushil Anirudh , Danai Koutra , Jayaraman J. Thiagarajan

Reinforcement learning algorithms based on Q-learning are driving Deep Reinforcement Learning (DRL) research towards solving complex problems and achieving super-human performance on many of them. Nevertheless, Q-Learning is known to be…

Machine Learning · Computer Science 2022-06-14 Andrea Cini , Carlo D'Eramo , Jan Peters , Cesare Alippi

Meta-reinforcement learning algorithms provide a data-driven way to acquire policies that quickly adapt to many tasks with varying rewards or dynamics functions. However, learned meta-policies are often effective only on the exact task…

Machine Learning · Computer Science 2023-07-13 Anurag Ajay , Abhishek Gupta , Dibya Ghosh , Sergey Levine , Pulkit Agrawal

Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time. Existing infinite-horizon methods, which often rely on discounted…

Machine Learning · Computer Science 2026-02-03 Jiamin Xu , Kyra Gan

Online reinforcement learning (RL) has been widely applied in information processing scenarios, which usually exhibit much uncertainty due to the intrinsic randomness of channels and service demands. In this paper, we consider an…

Machine Learning · Computer Science 2021-06-17 Rongpeng Li

Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically simpler, more flexible to use, and thus more…

Machine Learning · Computer Science 2018-07-11 Chi Jin , Zeyuan Allen-Zhu , Sebastien Bubeck , Michael I. Jordan

We study learning in periodic Markov Decision Process(MDP), a special type of non-stationary MDP where both the state transition probabilities and reward functions vary periodically, under the average reward maximization setting. We…

Machine Learning · Computer Science 2022-07-26 Ayush Aniket , Arpan Chattopadhyay

At the boundary between the known and the unknown, an agent inevitably confronts the dilemma of whether to explore or to exploit. Epistemic uncertainty reflects such boundaries, representing systematic uncertainty due to limited knowledge.…

Machine Learning · Computer Science 2026-03-03 Jianfei Ma , Wee Sun Lee