English
Related papers

Related papers: Infinite-Horizon Reinforcement Learning with Multi…

200 papers

We study the model-based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs). The oracle we consider is the optimal policy of the POMDP with a known environment in terms of the average reward over…

Machine Learning · Computer Science 2022-07-19 Yi Xiong , Ningyuan Chen , Xuefeng Gao , Xiang Zhou

We propose an epoch-based reinforcement learning algorithm for infinite-horizon average-cost Markov decision processes (MDPs) that leverages a partial order over a policy class. In this structure, $\pi' \leq \pi$ if data collected under…

Machine Learning · Statistics 2025-08-07 Zhongjun Zhang , Shipra Agrawal , Ilan Lobel , Sean R. Sinclair , Christina Lee Yu

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

We present two Policy Gradient-based algorithms with general parametrization in the context of infinite-horizon average reward Markov Decision Process (MDP). The first one employs Implicit Gradient Transport for variance reduction, ensuring…

Machine Learning · Computer Science 2025-05-13 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

Optimization and Control · Mathematics 2022-06-07 Hyeong Soo Chang

We study a new class of MDPs that employs multinomial logit (MNL) function approximation to ensure valid probability distributions over the state space. Despite its significant benefits, incorporating the non-linear function raises…

Machine Learning · Computer Science 2025-01-17 Long-Fei Li , Yu-Jie Zhang , Peng Zhao , Zhi-Hua Zhou

Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low…

Machine Learning · Computer Science 2021-01-05 Minbo Gao , Tianle Xie , Simon S. Du , Lin F. Yang

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

We consider online reinforcement learning in episodic Markov decision process (MDP) with unknown transition function and stochastic rewards drawn from some fixed but unknown distribution. The learner aims to learn the optimal policy and…

Machine Learning · Computer Science 2024-03-12 Vincent Leon , S. Rasoul Etesami

We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition probability can be parameterized as a linear function of a given…

Machine Learning · Computer Science 2023-11-07 Jiafan He , Heyang Zhao , Dongruo Zhou , Quanquan Gu

This paper investigates the potential of quantum acceleration in addressing infinite horizon Markov Decision Processes (MDPs) to enhance average reward outcomes. We introduce an innovative quantum framework for the agent's engagement with…

Machine Learning · Computer Science 2025-05-28 Bhargav Ganguly , Yang Xu , Vaneet Aggarwal

We study reinforcement learning in an infinite-horizon average-reward setting with linear function approximation, where the transition probability function of the underlying Markov Decision Process (MDP) admits a linear form over a feature…

Machine Learning · Computer Science 2022-05-11 Yue Wu , Dongruo Zhou , Quanquan Gu

Recently, model-free reinforcement learning has attracted research attention due to its simplicity, memory and computation efficiency, and the flexibility to combine with function approximation. In this paper, we propose Exploration…

Machine Learning · Computer Science 2020-12-10 Mehdi Jafarnia-Jahromi , Chen-Yu Wei , Rahul Jain , Haipeng Luo

This paper gives the first polynomial-time algorithm for tabular Markov Decision Processes (MDP) that enjoys a regret bound \emph{independent on the planning horizon}. Specifically, we consider tabular MDP with $S$ states, $A$ actions, a…

Machine Learning · Computer Science 2022-06-17 Zihan Zhang , Xiangyang Ji , Simon S. Du

Reinforcement learning with multinomial logistic (MNL) function approximation has become an important framework due to its flexibility and broad applicability. While existing studies have established regret guarantees under worst-case…

Machine Learning · Statistics 2026-05-28 Wonyoung Kim , Min-Hwan Oh , Garud Iyengar , Assaf Zeevi

We consider the problem of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves…

Machine Learning · Computer Science 2020-11-03 Chi Jin , Tiancheng Jin , Haipeng Luo , Suvrit Sra , Tiancheng Yu

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

Machine Learning · Computer Science 2023-06-05 Yan Dai , Haipeng Luo , Chen-Yu Wei , Julian Zimmert

A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a.k.a.~the horizon-free bounds. However, these regret bounds only apply to settings where a polynomial dependency on…

Machine Learning · Computer Science 2024-03-19 Zihan Zhang , Jason D. Lee , Yuxin Chen , Simon S. Du

We study reinforcement learning with linear function approximation where the transition probability and reward functions are linear with respect to a feature mapping $\boldsymbol{\phi}(s,a)$. Specifically, we consider the episodic…

Machine Learning · Computer Science 2023-01-31 Pihe Hu , Yu Chen , Longbo Huang