English
Related papers

Related papers: Bellman-consistent Pessimism for Offline Reinforce…

200 papers

Model-based offline reinforcement learning approaches generally rely on bounds of model error. Estimating these bounds is usually achieved through uncertainty estimation methods. In this work, we combine parametric and nonparametric methods…

Machine Learning · Computer Science 2022-11-07 Guy Tennenholtz , Shie Mannor

Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient methods do not handle off-policy data well, leading to premature…

Machine Learning · Computer Science 2025-01-28 Qing Wang , Yingru Li , Jiechao Xiong , Tong Zhang

The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online…

Machine Learning · Computer Science 2024-08-15 Shashank Gupta , Olivier Jeunen , Harrie Oosterhuis , Maarten de Rijke

A primary requirement for any reinforcement learning method is that it should produce policies that improve upon the initial guess. In this work, we show that the widely used Deep Q-Network (DQN) fails to satisfy this minimal criterion --…

Machine Learning · Computer Science 2025-06-18 Aditya Gopalan , Gugan Thoppe

Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigates the feasibility of using PPO for direct reinforcement…

Computation and Language · Computer Science 2024-10-23 Alexander G. Padula , Dennis J. N. J. Soemers

The key limitation of the verification performance lies in the ability of error detection. With this intuition we designed several variants of pessimistic verification, which are simple workflows that could significantly improve the…

Artificial Intelligence · Computer Science 2025-11-27 Yanxing Huang , Zihan Tang , Zejin Lin , Peng Li , Yang Liu

While offline reinforcement learning provides reliable policies for real-world deployment, its inherent pessimism severely restricts an agent's ability to explore and collect novel data online. Drawing inspiration from safe reinforcement…

Machine Learning · Computer Science 2026-03-20 Amirhossein Roknilamouki , Arnob Ghosh , Eylem Ekici , Ness B. Shroff

We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized with respect to a fixed reference policy through KL regularization. Prior work relies on pessimistic value estimation to handle distribution…

Computer Science and Game Theory · Computer Science 2026-05-11 Yuheng Zhang , Claire Chen , Nan Jiang

It is well known that the extension of Watkins' algorithm to general function approximation settings is challenging: does the projected Bellman equation have a solution? If so, is the solution useful in the sense of generating a good…

Optimization and Control · Mathematics 2020-08-11 Prashant G. Mehta , Sean P. Meyn

A precondition for the deployment of a Reinforcement Learning agent to a real-world system is to provide guarantees on the learning process. While a learning algorithm will eventually converge to a good policy, there are no guarantees on…

Machine Learning · Statistics 2023-12-27 Paul Daoudi , Mathias Formoso , Othman Gaizi , Achraf Azize , Evrard Garcelon

Modern reinforcement learning (RL) can be categorized into online and offline variants. As a pivotal aspect of both online and offline RL, current research on the Bellman equation revolves primarily around optimization techniques and…

Machine Learning · Computer Science 2023-12-14 Outongyi Lv , Bingxin Zhou

Offline reinforcement learning (RL) has received increasing attention for learning policies from previously collected data without interaction with the real environment, which is particularly important in high-stakes applications. While a…

Machine Learning · Computer Science 2026-04-03 Qing Zhu , Xian Yu

Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…

Machine Learning · Computer Science 2022-12-19 Ashish Kumar , Ilya Kuzovkin

Sample-efficiency guarantees for offline reinforcement learning (RL) often rely on strong assumptions on both the function classes (e.g., Bellman-completeness) and the data coverage (e.g., all-policy concentrability). Despite the recent…

Machine Learning · Computer Science 2022-06-29 Wenhao Zhan , Baihe Huang , Audrey Huang , Nan Jiang , Jason D. Lee

Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without further environment interaction. A key challenge is the distribution shift between the learned and behavior policies, leading to…

Machine Learning · Computer Science 2025-08-11 Haohui Chen , Zhiyong Chen

Discounted reinforcement learning is fundamentally incompatible with function approximation for control in continuing tasks. It is not an optimization problem in its usual formulation, so when using function approximation there is no…

Artificial Intelligence · Computer Science 2019-11-28 Abhishek Naik , Roshan Shariff , Niko Yasui , Hengshuai Yao , Richard S. Sutton

Continuous-time stochastic processes underlie many natural and engineered systems. In healthcare, autonomous driving, and industrial control, direct interaction with the environment is often unsafe or impractical, motivating offline…

Machine Learning · Statistics 2025-11-14 Nicolas Hoischen , Petar Bevanda , Max Beier , Stefan Sosnowski , Boris Houska , Sandra Hirche

Offline policy optimization could have a large impact on many real-world decision-making problems, as online learning may be infeasible in many applications. Importance sampling and its variants are a commonly used type of estimator in…

Machine Learning · Computer Science 2022-07-05 Yao Liu , Yannis Flet-Berliac , Emma Brunskill

Offline Reinforcement Learning (RL) is a promising approach for next-generation wireless networks, where online exploration is unsafe and large amounts of operational data can be reused across the model lifecycle. However, the behavior of…

Networking and Internet Architecture · Computer Science 2026-03-05 Nicolas Helson , Pegah Alizadeh , Anastasios Giovanidis