English
Related papers

Related papers: Span-Based Optimal Sample Complexity for Average R…

200 papers

The ability to compute reward-optimal policies for given and known finite Markov decision processes (MDPs) underpins a variety of applications across planning, controller synthesis, and verification. However, we often want policies (1) to…

Logic in Computer Science · Computer Science 2025-11-18 Linus Heck , Filip Macák , Milan Češka , Sebastian Junges

One of the challenges in online reinforcement learning (RL) is that the agent needs to trade off the exploration of the environment and the exploitation of the samples to optimize its behavior. Whether we optimize for regret, sample…

Machine Learning · Computer Science 2021-11-19 Jean Tarbouriech , Matteo Pirotta , Michal Valko , Alessandro Lazaric

We consider reinforcement learning in parameterized Markov Decision Processes (MDPs), where the parameterization may induce correlation across transition probabilities or rewards. Consequently, observing a particular state transition might…

Machine Learning · Statistics 2015-04-01 Aditya Gopalan , Shie Mannor

We propose a new regret minimization algorithm for episodic sparse linear Markov decision process (SMDP) where the state-transition distribution is a linear function of observed features. The only previously known algorithm for SMDP…

Machine Learning · Statistics 2023-10-25 Wonyoung Kim , Garud Iyengar , Assaf Zeevi

Policy Iteration (PI) is a widely used family of algorithms to compute optimal policies for Markov Decision Problems (MDPs). We derive upper bounds on the running time of PI on Deterministic MDPs (DMDPs): the class of MDPs in which every…

Discrete Mathematics · Computer Science 2023-10-10 Ritesh Goenka , Eashan Gupta , Sushil Khyalia , Pratyush Agarwal , Mulinti Shaik Wajid , Shivaram Kalyanakrishnan

In this paper, we consider a modified version of the control problem in a model free Markov decision process (MDP) setting with large state and action spaces. The control problem most commonly addressed in the contemporary literature is to…

Artificial Intelligence · Computer Science 2018-02-01 Ajin George Joseph , Shalabh Bhatnagar

Running machine learning algorithms on large and rapidly growing volumes of data is often computationally expensive, one common trick to reduce the size of a data set, and thus reduce the computational cost of machine learning algorithms,…

Machine Learning · Computer Science 2022-01-25 Shaojie Tang , Jing Yuan

We study infinite-horizon average-reward Markov decision processes (AMDPs) in the context of general function approximation. Specifically, we propose a novel algorithmic framework named Local-fitted Optimization with OPtimism (LOOP), which…

Machine Learning · Computer Science 2024-04-22 Jianliang He , Han Zhong , Zhuoran Yang

Calculating optimal policies is known to be computationally difficult for Markov decision processes (MDPs) with Borel state and action spaces. This paper studies finite-state approximations of discrete time Markov decision processes with…

Optimization and Control · Mathematics 2016-09-23 Naci Saldi , Serdar Yüksel , Tamás Linder

We present the first efficient averaging sampler that achieves asymptotically optimal randomness complexity and near-optimal sample complexity. For any $\delta < \varepsilon$ and any constant $\alpha > 0$, our sampler uses $m + O(\log (1 /…

Computational Complexity · Computer Science 2025-08-18 Zhiyang Xun , David Zuckerman

In this paper, we study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. The multi-batch reinforcement learning framework, where the agent…

Machine Learning · Computer Science 2022-10-18 Zihan Zhang , Yuhang Jiang , Yuan Zhou , Xiangyang Ji

We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner. We provide an algorithm that achieves state-of-the-art regret bound of $O( \sqrt{\tau (\ln|S|+\ln|A|)T}\ln(T))$, where $S$…

Machine Learning · Computer Science 2019-05-28 Adrian Rivera Cardoso , He Wang , Huan Xu

Policy Iteration (PI) is a classical family of algorithms to compute an optimal policy for any given Markov Decision Problem (MDP). The basic idea in PI is to begin with some initial policy and to repeatedly update the policy to one from an…

Within the framework of probably approximately correct Markov decision processes (PAC-MDP), much theoretical work has focused on methods to attain near optimality after a relatively long period of learning and exploration. However,…

Artificial Intelligence · Computer Science 2016-04-06 Kenji Kawaguchi

Markov decision processes (MDPs) are used to model a wide variety of applications ranging from game playing over robotics to finance. Their optimal policy typically maximizes the expected sum of rewards given at each step of the decision…

Machine Learning · Computer Science 2025-05-26 Maximilian Nägele , Jan Olle , Thomas Fösel , Remmy Zen , Florian Marquardt

Regularized MDPs serve as a smooth version of original MDPs. However, biased optimal policy always exists for regularized MDPs. Instead of making the coefficient{\lambda}of regularized term sufficiently small, we propose an adaptive…

Machine Learning · Computer Science 2020-11-03 Wenhao Yang , Xiang Li , Guangzeng Xie , Zhihua Zhang

Robust Markov decision processes (RMDPs) extend standard Markov decision processes (MDPs) to account for uncertainty in the transition probabilities. RMDPs have an uncertainty set that defines a set of possible transition functions, each of…

Logic in Computer Science · Computer Science 2026-04-30 Marnix Suilen , Guillermo A. Pérez

This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However,…

Machine Learning · Statistics 2024-03-11 Gen Li , Laixi Shi , Yuxin Chen , Yuejie Chi , Yuting Wei

We design fast algorithms for repeatedly sampling from strongly Rayleigh distributions, which include random spanning tree distributions and determinantal point processes. For a graph $G=(V, E)$, we show how to approximately sample…

Data Structures and Algorithms · Computer Science 2022-09-20 Nima Anari , Yang P. Liu , Thuy-Duong Vuong

We present a new algorithm based on posterior sampling for learning in Constrained Markov Decision Processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2024-05-30 Danil Provodin , Maurits Kaptein , Mykola Pechenizkiy