English
Related papers

Related papers: Regret Analysis of Policy Gradient Algorithm for I…

200 papers

We consider the problem of learning an unknown Markov Decision Process (MDP) that is weakly communicating in the infinite horizon setting. We propose a Thompson Sampling-based reinforcement learning algorithm with dynamic episodes (TSDE).…

Machine Learning · Computer Science 2017-09-15 Yi Ouyang , Mukul Gagrani , Ashutosh Nayyar , Rahul Jain

We address the problem of finding the optimal policy of a constrained Markov decision process (CMDP) using a gradient descent-based algorithm. Previous results have shown that a primal-dual approach can achieve an $\mathcal{O}(1/\sqrt{T})$…

Machine Learning · Computer Science 2022-02-07 Tao Liu , Ruida Zhou , Dileep Kalathil , P. R. Kumar , Chao Tian

We study sequential decision-making in time-varying Markov decision processes (TVMDPs) under limited update rates, where the decision-maker observes the system and updates its model only intermittently. Such settings arise in applications…

Systems and Control · Electrical Eng. & Systems 2026-04-16 Negin Musavi , Melkior Ornik

The infinite horizon setting is widely adopted for problems of reinforcement learning (RL). These invariably result in stationary policies that are optimal. In many situations, finite horizon control problems are of interest and for such…

Machine Learning · Computer Science 2025-03-21 Soumyajit Guin , Shalabh Bhatnagar

We consider the problem of finding the best memoryless stochastic policy for an infinite-horizon partially observable Markov decision process (POMDP) with finite state and action spaces with respect to either the discounted or mean reward…

Optimization and Control · Mathematics 2022-05-02 Johannes Müller , Guido Montúfar

We present an algorithm based on the \emph{Optimism in the Face of Uncertainty} (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision process (MDP) with finite state-action space efficiently. By…

Machine Learning · Computer Science 2020-01-01 Zihan Zhang , Xiangyang Ji

Risk-averse total-reward Markov Decision Processes (MDPs) offer a promising framework for modeling and solving undiscounted infinite-horizon objectives. Existing model-based algorithms for risk measures like the entropic risk measure (ERM)…

Machine Learning · Computer Science 2025-10-27 Xihong Su , Jia Lin Hau , Gersi Doko , Kishan Panaganti , Marek Petrik

We present an efficient reinforcement learning algorithm that learns the optimal admission control policy in a partially observable queueing network. Specifically, only the arrival and departure times from the network are observable, and…

Machine Learning · Computer Science 2023-08-07 Jonatha Anselmi , Bruno Gaujal , Louis-Sébastien Rebuffi

Deterministic Markov Decision Processes (DMDPs) are a mathematical framework for decision-making where the outcomes and future possible actions are deterministically determined by the current action taken. DMDPs can be viewed as a finite…

Artificial Intelligence · Computer Science 2025-06-17 Ali Asadi , Krishnendu Chatterjee , Jakob de Raaij

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

Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. Many successful reinforcement learning algorithms build on variations of policy-gradient methods, but…

Machine Learning · Computer Science 2024-05-15 Qiuhao Wang , Chin Pang Ho , Marek Petrik

We consider the problem of provably optimal exploration in reinforcement learning for finite horizon MDPs. We show that an optimistic modification to value iteration achieves a regret bound of $\tilde{O}( \sqrt{HSAT} + H^2S^2A+H\sqrt{T})$…

Machine Learning · Statistics 2017-07-04 Mohammad Gheshlaghi Azar , Ian Osband , Rémi Munos

We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the environment but cannot access the reward; and (2) in the…

Machine Learning · Computer Science 2024-02-15 Junkai Zhang , Weitong Zhang , Quanquan Gu

In this paper we prove the efficacy of a simple greedy algorithm for a finite horizon online resource allocation/matching problem, when the corresponding static planning linear program (SPP) exhibits a non-degeneracy condition called the…

Data Structures and Algorithms · Computer Science 2022-07-26 Varun Gupta

We introduce two new no-regret algorithms for the stochastic shortest path (SSP) problem with a linear MDP that significantly improve over the only existing results of (Vial et al., 2021). Our first algorithm is computationally efficient…

Machine Learning · Computer Science 2021-12-21 Liyu Chen , Rahul Jain , Haipeng Luo

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

We study reinforcement learning (RL) for decision processes with non-Markovian reward, in which high-level knowledge of the task in the form of reward machines is available to the learner. We consider probabilistic reward machines with…

Machine Learning · Computer Science 2024-12-30 Hippolyte Bourel , Anders Jonsson , Odalric-Ambrym Maillard , Chenxiao Ma , Mohammad Sadegh Talebi

We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high probability. We introduce an algorithm, Cert-LSVI-UCB, for…

Machine Learning · Computer Science 2024-12-13 Weitong Zhang , Zhiyuan Fan , Jiafan He , Quanquan Gu

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

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization poses significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon…

Optimization and Control · Mathematics 2026-03-10 Xin Chen , Yifan Hu , Minda Zhao