English
Related papers

Related papers: One-Step Bellman Alignment Enables Provably Effici…

200 papers

Transfer reinforcement learning (RL) methods leverage on the experience collected on a set of source tasks to speed-up RL algorithms. A simple and effective approach is to transfer samples from source tasks and include them into the…

Artificial Intelligence · Computer Science 2011-09-02 Alessandro Lazaric , Marcello Restelli

Multi-Task Learning (MTL) has achieved success in various fields. However, how to balance different tasks to achieve good performance is a key problem. To achieve the task balancing, there are many works to carefully design dynamical…

Machine Learning · Computer Science 2022-07-28 Baijiong Lin , Feiyang Ye , Yu Zhang , Ivor W. Tsang

For continuous action spaces, actor-critic methods are widely used in online reinforcement learning (RL). However, unlike RL algorithms for discrete actions, which generally model the optimal value function using the Bellman optimality…

Machine Learning · Computer Science 2025-08-14 Motoki Omura , Kazuki Ota , Takayuki Osa , Yusuke Mukuta , Tatsuya Harada

Deep reinforcement learning (RL) is a powerful approach to complex decision making. However, one issue that limits its practical application is its brittleness, sometimes failing to train in the presence of small changes in the environment.…

Machine Learning · Computer Science 2025-01-27 Jung-Hoon Cho , Vindula Jayawardana , Sirui Li , Cathy Wu

As with any machine learning problem with limited data, effective offline RL algorithms require careful regularization to avoid overfitting. One-step methods perform regularization by doing just a single step of policy improvement, while…

Machine Learning · Computer Science 2023-07-25 Benjamin Eysenbach , Matthieu Geist , Sergey Levine , Ruslan Salakhutdinov

Direct evaluation of LLMs on benchmarks can be misleading because comparatively strong performance may reflect task familiarity rather than capability. The train-before-test approach controls for task familiarity by giving each model…

Machine Learning · Computer Science 2026-03-16 Kun Wang , Reinhard Heckel

Estimating individualized treatment rules (ITRs) is fundamental to precision medicine, where the goal is to tailor treatment decisions to individual patient characteristics. While numerous methods have been developed for ITR estimation,…

Methodology · Statistics 2026-05-15 Eun Jeong Oh , Min Qian

We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an…

Machine Learning · Computer Science 2026-03-05 Shengbo Wang

One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates approximations to the optimal value function by solving a sequence of regression problems. To…

Machine Learning · Computer Science 2024-06-19 Noah Golowich , Ankur Moitra

Time-inhomogeneous finite-horizon Markov decision processes (MDP) are frequently employed to model decision-making in dynamic treatment regimes and other statistical reinforcement learning (RL) scenarios. These fields, especially healthcare…

Machine Learning · Computer Science 2025-10-21 Elynn Chen , Sai Li , Michael I. Jordan

Achieving fast and stable off-policy learning in deep reinforcement learning (RL) is challenging. Most existing methods rely on semi-gradient temporal-difference (TD) methods for their simplicity and efficiency, but are consequently…

Machine Learning · Computer Science 2025-09-22 Esraa Elelimy , Brett Daley , Andrew Patterson , Marlos C. Machado , Adam White , Martha White

The use of target networks in deep reinforcement learning is a widely popular solution to mitigate the brittleness of semi-gradient approaches and stabilize learning. However, target networks notoriously require additional memory and delay…

Machine Learning · Computer Science 2026-03-02 Théo Vincent , Yogesh Tripathi , Tim Faust , Abdullah Akgül , Yaniv Oren , Melih Kandemir , Jan Peters , Carlo D'Eramo

Reinforcement learning (RL) in robotics is often limited by the cost and risk of data collection, motivating experience transfer from a source task to a target task. Offline-to-online RL leverages prior data but typically assumes a given…

Machine Learning · Computer Science 2026-04-16 Mintae Kim , Koushil Sreenath

This paper develops an online inverse reinforcement learning algorithm aimed at efficiently recovering a reward function from ongoing observations of an agent's actions. To reduce the computation time and storage space in reward estimation,…

Robotics · Computer Science 2017-08-01 Kun Li , Joel W. Burdick

Reinforcement learning from human feedback (RLHF) has achieved great empirical success in aligning large language models (LLMs) with human preference, and it is of great importance to study the statistical efficiency of RLHF algorithms from…

Machine Learning · Computer Science 2025-06-02 Songtao Feng , Jie Fu

Value function approximation is important in modern reinforcement learning (RL) problems especially when the state space is (infinitely) large. Despite the importance and wide applicability of value function approximation, its theoretical…

Machine Learning · Computer Science 2023-02-24 Hanlin Zhu , Ruosong Wang , Jason D. Lee

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

We consider the regret minimization problem in reinforcement learning (RL) in the episodic setting. In many real-world RL environments, the state and action spaces are continuous or very large. Existing approaches establish regret…

Machine Learning · Computer Science 2022-06-29 Sayak Ray Chowdhury , Rafael Oliveira

We develop a framework for designing simple and efficient policies for a family of online allocation and pricing problems, that includes online packing, budget-constrained probing, dynamic pricing, and online contextual bandits with…

Optimization and Control · Mathematics 2020-08-03 Alberto Vera , Siddhartha Banerjee , Itai Gurvich

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…

Machine Learning · Computer Science 2023-10-11 Wenzhuo Zhou