English
Related papers

Related papers: Provably Efficient Exploration in Constrained Rein…

200 papers

We present the first gap-dependent analysis of regret and communication cost for on-policy federated $Q$-Learning in tabular episodic finite-horizon Markov decision processes (MDPs). Existing FRL methods focus on worst-case scenarios,…

Machine Learning · Statistics 2025-09-19 Haochen Zhang , Zhong Zheng , Lingzhou Xue

Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the…

Machine Learning · Computer Science 2022-04-21 Jiafan He , Dongruo Zhou , Quanquan Gu

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

This paper studies the problem of Anytime-Competitive Markov Decision Process (A-CMDP). Existing works on Constrained Markov Decision Processes (CMDPs) aim to optimize the expected reward while constraining the expected cost over random…

Machine Learning · Computer Science 2024-02-06 Jianyi Yang , Pengfei Li , Tongxin Li , Adam Wierman , Shaolei Ren

We consider reinforcement learning in an environment modeled by an episodic, finite, stage-dependent Markov decision process of horizon $H$ with $S$ states, and $A$ actions. The performance of an agent is measured by the regret after…

In this paper, we investigate the concentration properties of cumulative reward in Markov Decision Processes (MDPs), focusing on both asymptotic and non-asymptotic settings. We introduce a unified approach to characterize reward…

Machine Learning · Computer Science 2025-12-04 Borna Sayedana , Peter E. Caines , Aditya Mahajan

We derive sublinear regret bounds for undiscounted reinforcement learning in continuous state space. The proposed algorithm combines state aggregation with the use of upper confidence bounds for implementing optimism in the face of…

Machine Learning · Computer Science 2013-02-12 Ronald Ortner , Daniil Ryabko

Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a…

Machine Learning · Computer Science 2019-10-15 Young Hun Jung , Marc Abeille , Ambuj Tewari

In this work, we propose a novel inverse reinforcement learning (IRL) algorithm for constrained Markov decision process (CMDP) problems. In standard IRL problems, the inverse learner or agent seeks to recover the reward function of the MDP,…

Machine Learning · Computer Science 2024-01-08 Nirjhar Das , Arpan Chattopadhyay

We study online learning of finite Markov decision process (MDP) problems when a side information vector is available. The problem is motivated by applications such as clinical trials, recommendation systems, etc. Such applications have an…

Machine Learning · Computer Science 2014-06-27 Yasin Abbasi-Yadkori , Gergely Neu

A central issue lying at the heart of online reinforcement learning (RL) is data efficiency. While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these results is only guaranteed in a…

Machine Learning · Computer Science 2025-04-30 Zihan Zhang , Yuxin Chen , Jason D. Lee , Simon S. Du

This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm,…

Machine Learning · Computer Science 2021-11-10 Priyank Agrawal , Jinglin Chen , Nan Jiang

We introduce causal Markov Decision Processes (C-MDPs), a new formalism for sequential decision making which combines the standard MDP formulation with causal structures over state transition and reward functions. Many contemporary and…

Machine Learning · Statistics 2021-02-16 Yangyi Lu , Amirhossein Meisami , Ambuj Tewari

We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…

Machine Learning · Computer Science 2020-11-02 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang

The theory of reinforcement learning has focused on two fundamental problems: achieving low regret, and identifying $\epsilon$-optimal policies. While a simple reduction allows one to apply a low-regret algorithm to obtain an…

Machine Learning · Computer Science 2022-06-23 Andrew Wagenmaker , Max Simchowitz , Kevin Jamieson

In this paper, we prove the first Bayesian regret bounds for Thompson Sampling in reinforcement learning in a multitude of settings. We simplify the learning problem using a discrete set of surrogate environments, and present a refined…

Machine Learning · Statistics 2024-02-08 Ahmadreza Moradipari , Mohammad Pedramfar , Modjtaba Shokrian Zini , Vaneet Aggarwal

Learning Markov decision processes (MDP) in an adversarial environment has been a challenging problem. The problem becomes even more challenging with function approximation, since the underlying structure of the loss function and transition…

Machine Learning · Computer Science 2023-02-15 Fang Kong , Xiangcheng Zhang , Baoxiang Wang , Shuai Li

This paper presents new \emph{variance-aware} confidence sets for linear bandits and linear mixture Markov Decision Processes (MDPs). With the new confidence sets, we obtain the follow regret bounds: For linear bandits, we obtain an…

Machine Learning · Computer Science 2021-11-01 Zihan Zhang , Jiaqi Yang , Xiangyang Ji , Simon S. Du

We study online learning in \emph{constrained MDPs} (CMDPs), focusing on the goal of attaining sublinear strong regret and strong cumulative constraint violation. Differently from their standard (weak) counterparts, these metrics do not…

Machine Learning · Computer Science 2024-10-04 Francesco Emanuele Stradi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

This paper initiates the study of data-dependent regret bounds in constrained MAB settings. These bounds depend on the sequence of losses that characterize the problem instance. Thus, they can be much smaller than classical…

Machine Learning · Computer Science 2025-06-24 Gianmarco Genalti , Francesco Emanuele Stradi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti