English
Related papers

Related papers: Provably Efficient Reinforcement Learning with Mul…

200 papers

Strong worst-case performance bounds for episodic reinforcement learning exist but fortunately in practice RL algorithms perform much better than such bounds would predict. Algorithms and theory that provide strong problem-dependent bounds…

Machine Learning · Computer Science 2019-11-05 Andrea Zanette , Emma Brunskill

We study regret minimization for reinforcement learning (RL) in Latent Markov Decision Processes (LMDPs) with context in hindsight. We design a novel model-based algorithmic framework which can be instantiated with both a model-optimistic…

Machine Learning · Computer Science 2023-05-23 Runlong Zhou , Ruosong Wang , Simon S. Du

This work pioneers regret analysis of risk-sensitive reinforcement learning in partially observable environments with hindsight observation, addressing a gap in theoretical exploration. We introduce a novel formulation that integrates…

Machine Learning · Computer Science 2024-02-29 Tonghe Zhang , Yu Chen , Longbo Huang

In this paper, we study reinforcement learning in Markov Decision Processes with Probabilistic Reward Machines (PRMs), a form of non-Markovian reward commonly found in robotics tasks. We design an algorithm for PRMs that achieves a regret…

Machine Learning · Statistics 2024-08-21 Xiaofeng Lin , Xuezhou Zhang

We study time-inhomogeneous episodic reinforcement learning (RL) under general function approximation and sparse rewards. We design a new algorithm, Variance-weighted Optimistic $Q$-Learning (VO$Q$L), based on $Q$-learning and bound its…

Machine Learning · Computer Science 2022-12-13 Alekh Agarwal , Yujia Jin , Tong Zhang

Obtaining first-order regret bounds -- regret bounds scaling not as the worst-case but with some measure of the performance of the optimal policy on a given instance -- is a core question in sequential decision-making. While such bounds…

Machine Learning · Computer Science 2022-10-24 Andrew Wagenmaker , Yifang Chen , Max Simchowitz , Simon S. Du , Kevin Jamieson

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

We consider the multinomial logistic bandit problem in which a learner interacts with an environment by selecting actions to maximize expected rewards based on probabilistic feedback from multiple possible outcomes. In the binary setting,…

Machine Learning · Statistics 2026-02-25 Pierre Boudart , Pierre Gaillard , Alessandro Rudi

The problem of reinforcement learning in an unknown and discrete Markov Decision Process (MDP) under the average-reward criterion is considered, when the learner interacts with the system in a single stream of observations, starting from an…

Machine Learning · Statistics 2018-03-06 Mohammad Sadegh Talebi , Odalric-Ambrym Maillard

We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses in the bandit feedback setting. Specifically, we focus on linear mixture MDPs whose transition kernel is a linear mixture model.…

Machine Learning · Computer Science 2024-03-08 Long-Fei Li , Peng Zhao , Zhi-Hua Zhou

While numerous works have focused on devising efficient algorithms for reinforcement learning (RL) with uniformly bounded rewards, it remains an open question whether sample or time-efficient algorithms for RL with large state-action space…

Machine Learning · Computer Science 2024-03-08 Jiayi Huang , Han Zhong , Liwei Wang , Lin F. Yang

Recent studies have shown that episodic reinforcement learning (RL) is not more difficult than contextual bandits, even with a long planning horizon and unknown state transitions. However, these results are limited to either tabular Markov…

Machine Learning · Computer Science 2022-05-24 Dongruo Zhou , Quanquan Gu

We study episodic reinforcement learning in non-stationary linear (a.k.a. low-rank) Markov Decision Processes (MDPs), i.e, both the reward and transition kernel are linear with respect to a given feature map and are allowed to evolve either…

Machine Learning · Computer Science 2021-12-28 Ahmed Touati , Pascal Vincent

We study the multinomial logit (MNL) contextual bandit problem for sequential assortment selection. Although most existing research assumes utility functions to be linear in item features, this linearity assumption restricts the modeling of…

Machine Learning · Computer Science 2026-01-13 Taehyun Hwang , Dahngoon Kim , Min-hwan Oh

Recent studies have shown that episodic reinforcement learning (RL) is no harder than bandits when the total reward is bounded by $1$, and proved regret bounds that have a polylogarithmic dependence on the planning horizon $H$. However, it…

Machine Learning · Computer Science 2023-05-16 Kaixuan Ji , Qingyue Zhao , Jiafan He , Weitong Zhang , Quanquan Gu

We present the OMG-CMDP! algorithm for regret minimization in adversarial Contextual MDPs. The algorithm operates under the minimal assumptions of realizable function class and access to online least squares and log loss regression oracles.…

Machine Learning · Computer Science 2023-08-15 Orin Levy , Alon Cohen , Asaf Cassel , Yishay Mansour

We establish that an optimistic variant of Q-learning applied to a fixed-horizon episodic Markov decision process with an aggregated state representation incurs regret $\tilde{\mathcal{O}}(\sqrt{H^5 M K} + \epsilon HK)$, where $H$ is the…

Machine Learning · Statistics 2020-02-20 Shi Dong , Benjamin Van Roy , Zhengyuan Zhou

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

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized setting. However, the…

Machine Learning · Computer Science 2026-03-03 Kaixuan Ji , Qingyue Zhao , Heyang Zhao , Qiwei Di , Quanquan Gu

In this paper, we study the contextual multinomial logit (MNL) bandit problem in which a learning agent sequentially selects an assortment based on contextual information, and user feedback follows an MNL choice model. There has been a…

Machine Learning · Statistics 2025-10-17 Joongkyu Lee , Min-hwan Oh