paper-with-me

Papers

Operator Models for Continuous-Time Offline Reinforcement Learning

2025-11-13 · Nicolas Hoischen, Petar Bevanda, Max Beier, Stefan Sosnowski, Boris Houska, Sandra Hirche arxiv

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 reinforcement learning from historical data. However, there is limited statistical understanding of the approximation errors inherent in learning policies from offline datasets. We address this by linking reinforcement learning to the Hamilton-Jacobi-Bellman equation and proposing an operator-theoretic algorithm based on a simple dynamic programming recursion. Specifically, we represent our world model in terms of the infinitesimal generator of controlled diffusion processes learned in a reproducing kernel Hilbert space. By integrating statistical learning methods and operator theory, we establish global convergence of the value function and derive finite-sample guarantees with bounds tied to system properties such as smoothness and stability. Our theoretical and numerical results indicate that operator-based approaches may hold promise in solving offline reinforcement learning using continuous-time optimal control.

📄 PDF Abstract BibTeX arXiv:2511.10383

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningAutonomous Driving

Similar Papers 제목 키워드 기반

Robust Reinforcement Learning for Continuous Control with Model Misspecification

2019-06-18 · ICLR 2020 1 · Daniel J. Mankowitz, Nir Levine, Rae Jeong, Yuanyuan Shi 외

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifi…

continuous-controlContinuous ControlMuJoCoreinforcement-learning+2

Peng's Q($λ$) for Conservative Value Estimation in Offline Reinforcement Learning

2026-05-14 · Byeongchan Kim, Min-hwan Oh arxiv

We propose a model-free offline multi-step reinforcement learning (RL) algorithm, Conservative Peng's Q($λ$) (CPQL). Our algorithm adapts the Peng's Q($λ$) (PQL) operator for conservative value estimation as an alternati…

Reinforcement LearningOffline RL

Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning

2022-01-01 · Ziyang Tang, Yihao Feng, Qiang Liu

Reinforcement learning (RL) has drawn increasing interests in recent years due to its tremendous success in various applications. However, standard RL algorithms can only be applied for single reward function, and cannot…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations

2022-06-09 · Cong Lu, Philip J. Ball, Tim G. J. Rudner, Jack Parker-Holder 외

Offline reinforcement learning has shown great promise in leveraging large pre-collected datasets for policy learning, allowing agents to forgo often-expensive online data collection. However, offline reinforcement learn…

Benchmarkingcontinuous-controlContinuous ControlOffline RL+3

Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts

2025-12-02 · Zhongjian Qiao, Rui Yang, Jiafei Lyu, Xiu Li 외 arxiv

Single-domain offline reinforcement learning (RL) often suffers from limited data coverage, while cross-domain offline RL handles this issue by leveraging additional data from other domains with dynamics shifts. However,…

Reinforcement LearningOffline RL