English
Related papers

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

200 papers

In this work, we study offline reinforcement learning (RL) with zero-shot generalization property (ZSG), where the agent has access to an offline dataset including experiences from different environments, and the goal of the agent is to…

Machine Learning · Computer Science 2025-03-12 Zhiyong Wang , Chen Yang , John C. S. Lui , Dongruo Zhou

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…

Machine Learning · Computer Science 2020-11-24 Tianhe Yu , Garrett Thomas , Lantao Yu , Stefano Ermon , James Zou , Sergey Levine , Chelsea Finn , Tengyu Ma

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

We study off-policy evaluation (OPE) in the problem of slate contextual bandits where a policy selects multi-dimensional actions known as slates. This problem is widespread in recommender systems, search engines, marketing, to medical…

Machine Learning · Statistics 2024-02-20 Haruka Kiyohara , Masahiro Nomura , Yuta Saito

Optimistic initialisation is an effective strategy for efficient exploration in reinforcement learning (RL). In the tabular case, all provably efficient model-free algorithms rely on it. However, model-free deep RL algorithms do not use…

Machine Learning · Computer Science 2020-02-28 Tabish Rashid , Bei Peng , Wendelin Böhmer , Shimon Whiteson

Off-policy learning (OPL) in contextual bandits aims to learn a decision-making policy that maximizes the target rewards by using only historical interaction data collected under previously developed policies. Unfortunately, when rewards…

Machine Learning · Computer Science 2025-06-18 Rikiya Takehi , Masahiro Asami , Kosuke Kawakami , Yuta Saito

Learning from human feedback typically relies on preference optimization that constrains policy updates through token-level regularization. However, preference optimization for language models is particularly challenging because token-space…

Machine Learning · Computer Science 2026-02-03 Enyi Jiang , Yibo Jacky Zhang , Yinglun Xu , Andreas Haupt , Nancy Amato , Sanmi Koyejo

Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected…

Machine Learning · Computer Science 2023-03-15 Han Zheng , Xufang Luo , Pengfei Wei , Xuan Song , Dongsheng Li , Jing Jiang

Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of…

Machine Learning · Computer Science 2022-10-13 Jialong Wu , Haixu Wu , Zihan Qiu , Jianmin Wang , Mingsheng Long

Training reinforcement learning policies using environment interaction data collected from varying policies or dynamics presents a fundamental challenge. Existing works often overlook the distribution discrepancies induced by policy or…

Machine Learning · Computer Science 2024-05-30 Yu Luo , Tianying Ji , Fuchun Sun , Jianwei Zhang , Huazhe Xu , Xianyuan Zhan

We propose a model for making data acquisition decisions for variables in contextual stochastic optimisation problems. Data acquisition decisions are typically treated as separate and fixed. We explore problem settings in which the…

Optimization and Control · Mathematics 2025-04-22 Egon Peršak , Miguel F. Anjos

We study the off-policy evaluation problem---estimating the value of a target policy using data collected by another policy---under the contextual bandit model. We consider the general (agnostic) setting without access to a consistent model…

Machine Learning · Statistics 2017-11-15 Yu-Xiang Wang , Alekh Agarwal , Miroslav Dudik

Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms require repeated, costly calls to planning and statistical estimation oracles. While…

Machine Learning · Computer Science 2026-05-04 Haichen Hu , Jian Qian , David Simchi-Levi

A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in out-of-distribution (OOD) regions. While OOD samples may capture valid…

Artificial Intelligence · Computer Science 2026-05-11 Hongqiang Lin , Dongxu Zhang , Yiding Sun , Mingzhe Li , Ning Yang , Haijun Zhang

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

Machine Learning · Computer Science 2023-05-23 Germano Gabbianelli , Gergely Neu , Nneka Okolo , Matteo Papini

The dynamic portfolio optimization problem in finance frequently requires learning policies that adhere to various constraints, driven by investor preferences and risk. We motivate this problem of finding an allocation policy within a…

Artificial Intelligence · Computer Science 2020-12-23 Nymisha Bandi , Theja Tulabandhula

We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without assuming realizability or imposing model restrictions on losses or rewards. In this…

Machine Learning · Statistics 2026-04-06 Samuel Girard , Aurelien Bibaut , Arthur Gretton , Nathan Kallus , Houssam Zenati

Balancing performance and safety is crucial to deploying autonomous vehicles in multi-agent environments. In particular, autonomous racing is a domain that penalizes safe but conservative policies, highlighting the need for robust, adaptive…

Machine Learning · Computer Science 2020-08-25 Aman Sinha , Matthew O'Kelly , Hongrui Zheng , Rahul Mangharam , John Duchi , Russ Tedrake

Language model alignment methods such as reinforcement learning from human feedback (RLHF) have led to impressive advances in language model capabilities, but are limited by a widely observed phenomenon known as overoptimization, where the…

Artificial Intelligence · Computer Science 2025-02-19 Audrey Huang , Wenhao Zhan , Tengyang Xie , Jason D. Lee , Wen Sun , Akshay Krishnamurthy , Dylan J. Foster

Offline reinforcement learning (RL) aims to find optimal policies in dynamic environments in order to maximize the expected total rewards by leveraging pre-collected data. Learning from heterogeneous data is one of the fundamental…

Machine Learning · Statistics 2026-03-10 Rui Miao , Babak Shahbaba , Annie Qu