English
Related papers

Related papers: Oracle-Efficient Pessimism: Offline Policy Optimiz…

200 papers

We study the problem of policy evaluation and learning from batched contextual bandit data when treatments are continuous, going beyond previous work on discrete treatments. Previous work for discrete treatment/action spaces focuses on…

Machine Learning · Statistics 2018-02-19 Nathan Kallus , Angela Zhou

We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal…

Machine Learning · Computer Science 2011-06-17 Miroslav Dudik , Daniel Hsu , Satyen Kale , Nikos Karampatziakis , John Langford , Lev Reyzin , Tong Zhang

We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem. In this problem, the learner repeatedly makes an action on the basis of a context and receives reward for the…

Machine Learning · Computer Science 2016-02-09 Vasilis Syrgkanis , Akshay Krishnamurthy , Robert E. Schapire

We investigate the theoretical aspects of offline reinforcement learning (RL) under general function approximation. While prior works (e.g., Xie et al., 2021) have established the theoretical foundations of learning a good policy from…

Machine Learning · Computer Science 2026-05-11 Xiang Li , Yuheng Zhang , Nan Jiang

We consider the stochastic linear (multi-armed) contextual bandit problem with the possibility of hidden simple multi-armed bandit structure in which the rewards are independent of the contextual information. Algorithms that are designed…

Machine Learning · Statistics 2020-10-07 Niladri S. Chatterji , Vidya Muthukumar , Peter L. Bartlett

We study the offline reinforcement learning (offline RL) problem, where the goal is to learn a reward-maximizing policy in an unknown Markov Decision Process (MDP) using the data coming from a policy $\mu$. In particular, we consider the…

Machine Learning · Computer Science 2021-10-19 Ming Yin , Yu-Xiang Wang

Offline Preference-based Reinforcement Learning (PbRL) learns rewards and policies aligned with human preferences without the need for extensive reward engineering and direct interaction with human annotators. However, ensuring safety…

Artificial Intelligence · Computer Science 2025-12-24 Ze Gong , Pradeep Varakantham , Akshat Kumar

We study the $K$-armed contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only observes \emph{preference-based feedback} suggesting that one…

Machine Learning · Computer Science 2021-11-25 Aadirupa Saha , Akshay Krishnamurthy

We consider function optimization as a sequential decision making problem under budget constraint. This constraint limits the number of objective function evaluations allowed during the optimization. We consider an algorithm inspired by a…

Machine Learning · Computer Science 2026-05-06 Philippe Preux , Rémi Munos , Michal Valko

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Machine Learning · Computer Science 2025-03-18 Natinael Solomon Neggatu , Jeremie Houssineau , Giovanni Montana

Originating in the artificial intelligence literature, optimistic planning (OP) is an algorithm that generates near-optimal control inputs for generic nonlinear discrete-time systems whose input set is finite. This technique is therefore…

Optimization and Control · Mathematics 2019-08-06 Mathieu Granzotto , Romain Postoyan , Lucian Buşoniu , Dragan Nešić , Jamal Daafouz

We study contextual online pricing with biased offline data. For the scalar price elasticity case, we identify the instance-dependent quantity $\delta^2$ that measures how far the offline data lies from the (unknown) online optimum. We show…

Machine Learning · Computer Science 2025-07-04 Yixuan Zhang , Ruihao Zhu , Qiaomin Xie

Recent work shows that when contexts are drawn i.i.d., linear contextual bandits can be reduced to single-context linear bandits. This ``contexts are cheap" perspective is highly advantageous, as it allows for sharper finite-time analyses…

Machine Learning · Computer Science 2026-03-16 Kaan Buyukkalayci , Osama Hanna , Christina Fragouli

We consider the fundamental problem of prediction with expert advice where the experts are "optimizable": there is a black-box optimization oracle that can be used to compute, in constant time, the leading expert in retrospect at any point…

Machine Learning · Computer Science 2016-01-28 Elad Hazan , Tomer Koren

Existing offline reinforcement learning (RL) methods face a few major challenges, particularly the distributional shift between the learned policy and the behavior policy. Offline Meta-RL is emerging as a promising approach to address these…

Machine Learning · Computer Science 2022-07-14 Sen Lin , Jialin Wan , Tengyu Xu , Yingbin Liang , Junshan Zhang

Reinforcement-learning (RL) agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR) which trains the policy across many simulators produced by…

Machine Learning · Computer Science 2026-02-05 Arnaud Fickinger , Abderrahim Bendahi , Stuart Russell

Conservatism has led to significant progress in offline reinforcement learning (RL) where an agent learns from pre-collected datasets. However, as many real-world scenarios involve interaction among multiple agents, it is important to…

Machine Learning · Computer Science 2022-04-05 Ling Pan , Longbo Huang , Tengyu Ma , Huazhe Xu

We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Aviv Rosenberg , Alon Cohen , Yishay Mansour

We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that reduces contextual bandit learning with general reward function approximation to offline regression. The framework allows near-optimal regret for contextual…

Machine Learning · Computer Science 2026-02-11 Hao Qin , Chicheng Zhang

The proximal policy optimization (PPO) algorithm stands as one of the most prosperous methods in the field of reinforcement learning (RL). Despite its success, the theoretical understanding of PPO remains deficient. Specifically, it is…

Machine Learning · Computer Science 2023-06-09 Han Zhong , Tong Zhang