English
Related papers

Related papers: Trust the Model Where It Trusts Itself -- Model-Ba…

200 papers

Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning. Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as…

Computation and Language · Computer Science 2025-05-28 Zhiyuan Hu , Yibo Wang , Hanze Dong , Yuhui Xu , Amrita Saha , Caiming Xiong , Bryan Hooi , Junnan Li

Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent…

Robotics · Computer Science 2022-05-31 Haochen Liu , Zhiyu Huang , Jingda Wu , Chen Lv

Reinforcement learning (RL) algorithms have been successfully used to develop control policies for dynamical systems. For many such systems, these policies are trained in a simulated environment. Due to discrepancies between the simulated…

Systems and Control · Electrical Eng. & Systems 2020-11-23 Anubhav Guha , Anuradha Annaswamy

Animals and robots exist in a physical world and must coordinate their bodies to achieve behavioral objectives. With recent developments in deep reinforcement learning, it is now possible for scientists and engineers to obtain sensorimotor…

Robotics · Computer Science 2024-05-21 Yusheng Jiao , Feng Ling , Sina Heydari , Nicolas Heess , Josh Merel , Eva Kanso

Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in…

Robotics · Computer Science 2026-03-24 Zhilong Zhang , Haoxiang Ren , Yihao Sun , Yifei Sheng , Haonan Wang , Haoxin Lin , Zhichao Wu , Pierre-Luc Bacon , Yang Yu

The intrinsic high dimension of fluid dynamics is an inherent challenge to control of aerodynamic flows, and this is further complicated by a flow's nonlinear response to strong disturbances. Deep reinforcement learning, which takes…

Fluid Dynamics · Physics 2025-07-28 Zhecheng Liu , Diederik Beckers , Jeff D. Eldredge

Model-based Reinforcement Learning (MBRL) has been widely adapted due to its sample efficiency. However, existing worst-case regret analysis typically requires optimistic planning, which is not realistic in general. In contrast, motivated…

Machine Learning · Statistics 2023-01-10 Lingxiao Wang , Ping Li

The rapid development of machine learning (ML) and artificial intelligence (AI) applications requires the training of large numbers of models. This growing demand highlights the importance of training models without human supervision, while…

Machine Learning · Computer Science 2025-05-26 Alexey Boldyrev , Fedor Ratnikov , Andrey Shevelev

A limitation of model-based reinforcement learning (MBRL) is the exploitation of errors in the learned models. Black-box models can fit complex dynamics with high fidelity, but their behavior is undefined outside of the data…

Robotics · Computer Science 2020-11-04 Michael Lutter , Johannes Silberbauer , Joe Watson , Jan Peters

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and…

Machine Learning · Computer Science 2024-11-25 Maryam Shoaeinaeini , Brent Harrison

In this paper, a continuous-time adaptive actor-critic reinforcement learning (RL) controller is developed for drift-free nonlinear systems. Practical examples of such systems are image-based visual servoing (IBVS) and wheeled mobile robots…

Systems and Control · Electrical Eng. & Systems 2024-06-14 Ashwin P. Dani , Shubhendu Bhasin

Accurately simulating diverse behaviors of heterogeneous agents in various scenarios is fundamental to autonomous driving simulation. This task is challenging due to the multi-modality of behavior distribution, the high-dimensionality of…

Robotics · Computer Science 2024-10-27 Baotian He , Yibing Li

Model-based reinforcement learning (MBRL) is sample-efficient but depends on the accuracy of the learned dynamics, which are often modeled using black-box methods that do not adhere to physical laws. Those methods tend to produce inaccurate…

Systems and Control · Electrical Eng. & Systems 2026-03-10 Shreya Das , Kundan Kumar , Muhammad Iqbal , Outi Savolainen , Dominik Baumann , Laura Ruotsalainen , Simo Särkkä

Reinforcement learning (RL) is increasingly applied to real-world problems involving complex and structured decisions, such as routing, scheduling, and assortment planning. These settings challenge standard RL algorithms, which struggle to…

Machine Learning · Computer Science 2025-10-29 Heiko Hoppe , Léo Baty , Louis Bouvier , Axel Parmentier , Maximilian Schiffer

Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined…

Machine Learning · Computer Science 2018-03-02 Vladimir Feinberg , Alvin Wan , Ion Stoica , Michael I. Jordan , Joseph E. Gonzalez , Sergey Levine

Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrelevant for policy improvement. We instead propose a new…

Machine Learning · Computer Science 2023-05-23 Yecheng Jason Ma , Kausik Sivakumar , Jason Yan , Osbert Bastani , Dinesh Jayaraman

Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even leading to…

Computation and Language · Computer Science 2025-10-22 Wenhan Ma , Hailin Zhang , Liang Zhao , Yifan Song , Yudong Wang , Zhifang Sui , Fuli Luo

Learning systems are typically optimized by minimizing loss or maximizing reward, assuming that improvements in these signals reflect progress toward the true objective. However, when feedback reliability is unobservable, this assumption…

Machine Learning · Computer Science 2026-03-24 Zhipeng Zhang , Zhenjie Yao , Kai Li , Lei Yang

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

Machine Learning · Computer Science 2025-09-09 Stephan Rabanser

We introduce a Bayesian (deep) model-based reinforcement learning method (RoMBRL) that can capture model uncertainty to achieve sample-efficient policy optimisation. We propose to formulate the model-based policy optimisation problem as a…

Robotics · Computer Science 2021-01-06 Tai Hoang , Ngo Anh Vien