English
Related papers

Related papers: An Information-Theoretic Analysis of Bayesian Rein…

200 papers

We study online reinforcement learning in linear Markov decision processes with adversarial losses and bandit feedback, without prior knowledge on transitions or access to simulators. We introduce two algorithms that achieve improved regret…

Machine Learning · Computer Science 2023-10-19 Haolin Liu , Chen-Yu Wei , Julian Zimmert

Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether…

Machine Learning · Statistics 2024-08-09 Kevin Tan , Wei Fan , Yuting Wei

The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation systems. A major limitation of the AMDP formalism, however, is…

Machine Learning · Statistics 2024-05-06 Sang Bin Moon , Abolfazl Hashemi

We consider online learning for minimizing regret in unknown, episodic Markov decision processes (MDPs) with continuous states and actions. We develop variants of the UCRL and posterior sampling algorithms that employ nonparametric Gaussian…

Machine Learning · Computer Science 2019-01-04 Sayak Ray Chowdhury , Aditya Gopalan

In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order…

Optimization and Control · Mathematics 2010-11-23 Wenhan Dai , Yi Gai , Bhaskar Krishnamachari , Qing Zhao

In this work, we consider the regret minimization problem for reinforcement learning in latent Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of $M$ possible MDPs at the beginning of the interaction, but…

Machine Learning · Computer Science 2021-02-10 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

We study how to make decisions that minimize Bayesian regret in offline linear bandits. Prior work suggests that one must take actions with maximum lower confidence bound (LCB) on their reward. We argue that the reliance on LCB is…

Machine Learning · Computer Science 2024-07-04 Marek Petrik , Guy Tennenholtz , Mohammad Ghavamzadeh

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been…

Artificial Intelligence · Computer Science 2016-09-28 Michael Castronovo , Damien Ernst , Adrien Couetoux , Raphael Fonteneau

This paper considers the use of a simple posterior sampling algorithm to balance between exploration and exploitation when learning to optimize actions such as in multi-armed bandit problems. The algorithm, also known as Thompson Sampling,…

Machine Learning · Computer Science 2014-02-04 Daniel Russo , Benjamin Van Roy

In this paper, we consider the problem of optimization and learning for constrained and multi-objective Markov decision processes, for both discounted rewards and expected average rewards. We formulate the problems as zero-sum games where…

Optimization and Control · Mathematics 2021-03-05 Ather Gattami , Qinbo Bai , Vaneet Agarwal

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve over time but their…

Machine Learning · Computer Science 2024-04-16 Huozhi Zhou , Jinglin Chen , Lav R. Varshney , Ashish Jagmohan

In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world…

Machine Learning · Computer Science 2024-10-29 Yuting Tang , Xin-Qiang Cai , Yao-Xiang Ding , Qiyu Wu , Guoqing Liu , Masashi Sugiyama

We consider reinforcement learning for continuous-time Markov decision processes (MDPs) in the infinite-horizon, average-reward setting. In contrast to discrete-time MDPs, a continuous-time process moves to a state and stays there for a…

Machine Learning · Computer Science 2024-07-03 Xuefeng Gao , Xun Yu Zhou

In online reinforcement learning, data scarcity creates epistemic uncertainty that makes robustness important early in learning, whereas sufficient exploration is needed to learn the true-environment optimal policy. We study this…

Machine Learning · Computer Science 2026-05-26 Meichen Song , Yuhao Wang , Enlu Zhou

We consider the classic online learning and stochastic multi-armed bandit (MAB) problems, when at each step, the online policy can probe and find out which of a small number ($k$) of choices has better reward (or loss) before making its…

Data Structures and Algorithms · Computer Science 2022-11-08 Aditya Bhaskara , Sreenivas Gollapudi , Sungjin Im , Kostas Kollias , Kamesh Munagala

We develop a novel and generic algorithm for the adversarial multi-armed bandit problem (or more generally the combinatorial semi-bandit problem). When instantiated differently, our algorithm achieves various new data-dependent regret…

Machine Learning · Computer Science 2018-06-08 Chen-Yu Wei , Haipeng Luo

We consider the adversarial online multi-task reinforcement learning setting, where in each of $K$ episodes the learner is given an unknown task taken from a finite set of $M$ unknown finite-horizon MDP models. The learner's objective is to…

Machine Learning · Computer Science 2023-01-12 Quan Nguyen , Nishant A. Mehta

We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…

Machine Learning · Computer Science 2026-05-08 Harin Lee , Min-hwan Oh

We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our…

Machine Learning · Computer Science 2020-04-01 Shipra Agrawal , Randy Jia

Most bandit algorithm designs are purely theoretical. Therefore, they have strong regret guarantees, but also are often too conservative in practice. In this work, we pioneer the idea of algorithm design by minimizing the empirical Bayes…

Machine Learning · Computer Science 2020-06-12 Chih-Wei Hsu , Branislav Kveton , Ofer Meshi , Martin Mladenov , Csaba Szepesvari