English
Related papers

Related papers: Improved Regret Bounds for Linear Adversarial MDPs…

200 papers

In order to make good decision under uncertainty an agent must learn from observations. To do so, two of the most common frameworks are Contextual Bandits and Markov Decision Processes (MDPs). In this paper, we study whether there exist…

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

Policy optimization is a widely-used method in reinforcement learning. Due to its local-search nature, however, theoretical guarantees on global optimality often rely on extra assumptions on the Markov Decision Processes (MDPs) that bypass…

Machine Learning · Computer Science 2021-07-20 Haipeng Luo , Chen-Yu Wei , Chung-Wei Lee

We study online finite-horizon Markov Decision Processes with adversarially changing loss and aggregate bandit feedback (a.k.a full-bandit). Under this type of feedback, the agent observes only the total loss incurred over the entire…

Machine Learning · Computer Science 2025-02-07 Tal Lancewicki , Yishay Mansour

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

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

Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime…

Machine Learning · Computer Science 2023-02-22 Heyang Zhao , Jiafan He , Dongruo Zhou , Tong Zhang , Quanquan Gu

We derive a novel asymptotic problem-dependent lower-bound for regret minimization in finite-horizon tabular Markov Decision Processes (MDPs). While, similar to prior work (e.g., for ergodic MDPs), the lower-bound is the solution to an…

Machine Learning · Computer Science 2021-06-25 Andrea Tirinzoni , Matteo Pirotta , Alessandro Lazaric

We study online learning in finite-horizon episodic Markov decision processes (MDPs) under the challenging aggregate bandit feedback model, where the learner observes only the cumulative loss incurred in each episode, rather than individual…

Machine Learning · Computer Science 2025-10-28 Shinji Ito , Kevin Jamieson , Haipeng Luo , Arnab Maiti , Taira Tsuchiya

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear Markov decision processes (MDPs) and linear mixture MDPs under the Bellman optimality condition. While guaranteeing computational…

Machine Learning · Computer Science 2024-09-25 Woojin Chae , Dabeen Lee

We study a novel variant of online finite-horizon Markov Decision Processes with adversarially changing loss functions and initially unknown dynamics. In each episode, the learner suffers the loss accumulated along the trajectory realized…

Machine Learning · Computer Science 2021-02-02 Alon Cohen , Haim Kaplan , Tomer Koren , Yishay Mansour

We study regret minimization for infinite-horizon average-reward Markov Decision Processes (MDPs) under cost constraints. We start by designing a policy optimization algorithm with carefully designed action-value estimator and bonus term,…

Machine Learning · Computer Science 2022-02-02 Liyu Chen , Rahul Jain , Haipeng Luo

We develop a novel and generic algorithm for the adversarial multi-armed bandit problem (or more generally the combinatorial semi-bandit problem). When instantiated differently, our algorithm achieves various new data-dependent regret…

Machine Learning · Computer Science 2018-06-08 Chen-Yu Wei , Haipeng Luo

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

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

Machine Learning · Computer Science 2026-03-30 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

We investigate the hardness of online reinforcement learning in fixed horizon, sparse linear Markov decision process (MDP), with a special focus on the high-dimensional regime where the ambient dimension is larger than the number of…

Machine Learning · Computer Science 2021-02-11 Botao Hao , Tor Lattimore , Csaba Szepesvári , Mengdi Wang

We introduce the problem of regret minimization in adversarial multi-dueling bandits. While adversarial preferences have been studied in dueling bandits, they have not been explored in multi-dueling bandits. In this setting, the learner is…

Machine Learning · Computer Science 2024-06-27 Pratik Gajane

In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear regret and sublinear constraint violation, when competing…

Machine Learning · Computer Science 2024-09-27 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the…

Machine Learning · Computer Science 2021-10-19 Shuang Qiu , Xiaohan Wei , Zhuoran Yang , Jieping Ye , Zhaoran Wang

Reinforcement learning typically assumes that agents observe feedback for their actions immediately, but in many real-world applications (like recommendation systems) feedback is observed in delay. This paper studies online learning in…

Machine Learning · Computer Science 2021-12-16 Tal Lancewicki , Aviv Rosenberg , Yishay Mansour

We study online learning in constrained Markov decision processes (CMDPs) with adversarial losses and stochastic hard constraints, under bandit feedback. We consider three scenarios. In the first one, we address general CMDPs, where we…

Machine Learning · Computer Science 2025-02-10 Francesco Emanuele Stradi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti