English
Related papers

Related papers: Improved Regret Bound and Experience Replay in Reg…

200 papers

We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both "easy" and…

Machine Learning · Computer Science 2012-07-03 Gabor Bartok , Navid Zolghadr , Csaba Szepesvari

We study reinforcement learning with multinomial logistic (MNL) function approximation where the underlying transition probability kernel of the Markov decision processes (MDPs) is parametrized by an unknown transition core with features of…

Machine Learning · Statistics 2024-11-01 Wooseong Cho , Taehyun Hwang , Joongkyu Lee , Min-hwan Oh

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

In this paper, for POMDPs, we provide the convergence of a Q learning algorithm for control policies using a finite history of past observations and control actions, and, consequentially, we establish near optimality of such limit Q…

Machine Learning · Computer Science 2022-10-27 Ali Devran Kara , Serdar Yuksel

Policy Optimization (PO) methods are among the most popular Reinforcement Learning (RL) algorithms in practice. Recently, Sherman et al. [2023a] proposed a PO-based algorithm with rate-optimal regret guarantees under the linear Markov…

Machine Learning · Computer Science 2024-07-04 Asaf Cassel , Aviv Rosenberg

Policy Optimization (PO) is one of the most popular methods in Reinforcement Learning (RL). Thus, theoretical guarantees for PO algorithms have become especially important to the RL community. In this paper, we study PO in adversarial MDPs…

Machine Learning · Computer Science 2023-05-16 Tal Lancewicki , Aviv Rosenberg , Dmitry Sotnikov

In online inverse linear optimization, a learner observes time-varying sets of feasible actions and an agent's optimal actions, selected by solving linear optimization over the feasible actions. The learner sequentially makes predictions of…

Machine Learning · Computer Science 2025-05-23 Shinsaku Sakaue , Taira Tsuchiya , Han Bao , Taihei Oki

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

Machine Learning · Statistics 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

We consider the dynamic resource allocation problem where the decision space is finite-dimensional, yet the solution must satisfy a large or even infinite number of constraints revealed via streaming data or oracle feedback. We model this…

Machine Learning · Computer Science 2026-03-18 Yiming Zong , Jiashuo Jiang

We study online reinforcement learning for finite-horizon deterministic control systems with {\it arbitrary} state and action spaces. Suppose that the transition dynamics and reward function is unknown, but the state and action space is…

Machine Learning · Computer Science 2019-05-07 Lin F. Yang , Chengzhuo Ni , Mengdi Wang

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

We study the problem of learning Markov decision processes with finite state and action spaces when the transition probability distributions and loss functions are chosen adversarially and are allowed to change with time. We introduce an…

Machine Learning · Computer Science 2013-03-14 Yasin Abbasi-Yadkori , Peter L. Bartlett , Csaba Szepesvari

In this paper, we consider an online optimization problem over $T$ rounds where at each step $t\in[T]$, the algorithm chooses an action $x_t$ from the fixed convex and compact domain set $\mathcal{K}$. A utility function $f_t(\cdot)$ is…

Machine Learning · Computer Science 2021-06-16 Omid Sadeghi , Prasanna Raut , Maryam Fazel

We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature…

Machine Learning · Computer Science 2026-05-18 Rahul Singh , Siddharth Chandak , Eric Moulines , Vivek S. Borkar , Nicholas Bambos

This paper studies an online learning problem that seeks optimal testing policies for a stream of subjects, each of whom can be evaluated through a sequence of candidate tests drawn from a common pool. We refer to this problem as the Online…

Machine Learning · Computer Science 2025-09-05 Qiyuan Chen , Raed Al Kontar

Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be efficient in terms of statistical complexity, computational complexity, and query complexity. In this work, we consider the RLHF setting where the feedback…

Machine Learning · Computer Science 2024-03-14 Runzhe Wu , Wen Sun

In this paper we consider multi-objective reinforcement learning where the objectives are balanced using preferences. In practice, the preferences are often given in an adversarial manner, e.g., customers can be picky in many applications.…

Machine Learning · Computer Science 2021-10-29 Jingfeng Wu , Vladimir Braverman , Lin F. Yang

In this paper, we investigate the problem of \textit{episodic reinforcement learning} with quantum oracles for state evolution. To this end, we propose an \textit{Upper Confidence Bound} (UCB) based quantum algorithmic framework to…

Machine Learning · Computer Science 2023-02-20 Bhargav Ganguly , Yulian Wu , Di Wang , Vaneet Aggarwal

In the convex optimization approach to online regret minimization, many methods have been developed to guarantee a $O(\sqrt{T})$ bound on regret for subdifferentiable convex loss functions with bounded subgradients, by using a reduction to…

Machine Learning · Computer Science 2016-09-20 Arthur Flajolet , Patrick Jaillet

In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which…

Machine Learning · Statistics 2013-07-19 Mohammad Gheshlaghi Azar , Alessandro Lazaric , Emma Brunskill