世界模型

Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift

检测容易，适应困难：基于视觉模型的强化学习在分布偏移下的局部专家增长

Haiyang Zhao

机构 * University of Georgia（佐治亚大学） 纠错

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

AI总结 本文研究了视觉模型强化学习在分布偏移下的适应问题，提出JEPA-Indexed Local Expert Growth方法，通过局部专家进行动作修正，提升了对偏移环境的鲁棒性。

Cross-fitted Proximal Learning for Model-Based Reinforcement Learning

基于交叉验证的近端学习用于基于模型的强化学习

Nishanth Venkatesh, Andreas A. Malikopoulos

机构 * Cornell University（康奈尔大学） 纠错

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

AI总结 本文提出一种交叉验证的近端学习方法，用于解决基于模型的强化学习中因隐藏混淆导致的模型偏差问题，通过更高效利用数据提高估计精度。

Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial Optimization

在分支定界中的规划：基于模型的强化学习用于精确组合优化

Paul Strang, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum, Emmanuel Rachelson

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

AI总结 本文提出PlanB&B，一种基于模型的强化学习方法，用于改进分支定界中的分支策略，通过在四个标准MILP基准上优于现有方法的实验验证其有效性。

LD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse Observations

LD-EnSF：融合潜在动力学与集成评分滤波器用于稀疏观测的快速数据同化

Pengpeng Xiao, Phillip Si, Peng Chen

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Yale University（耶鲁大学） 纠错

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

AI总结 LD-EnSF通过在潜在空间中直接演进动力学，结合改进的LDNets和历史感知LSTM编码器，实现高维稀疏观测下的高效数据同化。

Causal Model-Based Reinforcement Learning for Sample-Efficient IoT Channel Access

Aswin Arun, Christo Kurisummoottil Thomas, Rimalpudi Sarvendranath, Walid Saad

机构 * Department of Electrical Engineering, Indian Institute of Technology, Tirupati, Andhra Pradesh, India（电子工程系，印度理工学院，蒂鲁帕蒂，安得拉邦，印度） ； Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA（电气与计算机工程系，沃思堡理工大学，沃思堡，马萨诸塞州，美国） ； Department of Electrical and Computer Engineering, Virginia Tech, Alexandria, VA, USA（电气与计算机工程系，弗吉尼亚理工大学，亚历山大，弗吉尼亚州，美国） 纠错

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

GALDS: A Graph-Autoencoder-based Latent Dynamics Surrogate model to predict neurite material transport

Tsung Yeh Hsieh, Yongjie Jessica Zhang

机构 * Department of Mechanical Engineering, Carnegie Mellon University（机械工程系，卡内基梅隆大学） ； Department of Biomedical Engineering, Carnegie Mellon University（生物医学工程系，卡内基梅隆大学） ； Department of Civil and Environmental Engineering, Carnegie Mellon University（土木与环境工程系，卡内基梅隆大学） 纠错

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning

Menglong Zhang, Fuyuan Qian

机构 * Southern University of Science and Technology（南方科技大学） 纠错

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.AI

Comments ICLR2025 https://openreview.net/forum?id=5YbuOTUFQ4

LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World

Taisuke Kobayashi

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.RO

Comments 21 pages, 17 figures (accepted in Robotics and Autonomous Systems)

Journal ref Robotics and Autonomous Systems, 2025

Data-Assimilated Model-Based Reinforcement Learning for Partially Observed Chaotic Flows

Defne E. Ozan, Andrea Nóvoa, Luca Magri

机构 * Imperial College London（帝国理工学院伦敦校区） ； The Alan Turing Institute（阿兰·图灵研究所） ； Politecnico di Torino（托里尼Politecnico） 纠错

专题命中 模型式强化学习 ：model-based reinforcement learning(title)；model-based RL(abstract)；分类 cs.LG

Learning global control of underactuated systems with Model-Based Reinforcement Learning

Niccolò Turcato, Marco Calì, Alberto Dalla Libera, Giulio Giacomuzzo, Ruggero Carli, Diego Romeres

专题命中 模型式强化学习 ：model-based reinforcement learning(title)；分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

Comments arXiv admin note: substantial text overlap with arXiv:2409.05811

On Rollouts in Model-Based Reinforcement Learning

Bernd Frauenknecht, Devdutt Subhasish, Friedrich Solowjow, Sebastian Trimpe

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecasting

Guang Zhao, Xihaier Luo, Seungjun Lee, Yihui Ren, Shinjae Yoo, Luke Van Roekel, Balu Nadiga, Sri Hari Krishna Narayanan, Yixuan Sun, Wei Xu

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

Multi-agent Uncertainty-Aware Pessimistic Model-Based Reinforcement Learning for Connected Autonomous Vehicles

Ruoqi Wen, Rongpeng Li, Xing Xu, Zhifeng Zhao

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.MA

Comments 17 pages, 7 figures

Data efficient Robotic Object Throwing with Model-Based Reinforcement Learning

Niccolò Turcato, Giulio Giacomuzzo, Matteo Terreran, Davide Allegro, Ruggero Carli, Alberto Dalla Libera

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.RO

Comments Preprint under review

EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning

Siddharth Aravindan, Dixant Mittal, Wee Sun Lee

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

Journal ref Asian Conference on Machine Learning 2024

Digital Twin Calibration with Model-Based Reinforcement Learning

Hua Zheng, Wei Xie, Ilya O. Ryzhov, Keilung Choy

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

Comments 28 pages, 6 figures

Parametric Taylor series based latent dynamics identification neural networks

Xinlei Lin, Dunhui Xiao

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

Functional Latent Dynamics for Irregularly Sampled Time Series Forecasting

Christian Klötergens, Vijaya Krishna Yalavarthi, Maximilian Stubbemann, Lars Schmidt-Thieme

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

Learning control of underactuated double pendulum with Model-Based Reinforcement Learning

Niccolò Turcato, Alberto Dalla Libera, Giulio Giacomuzzo, Ruggero Carli, Diego Romeres

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.RO

Liquid Fourier Latent Dynamics Networks for fast GPU-based numerical simulations in computational cardiology

Matteo Salvador, Alison L. Marsden

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

Identifying Ordinary Differential Equations for Data-efficient Model-based Reinforcement Learning

Tobias Nagel, Marco F. Huber

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；dynamics model(abstract)

Comments 10 pages, 6 figures, accepted at the IEEE World Congress on Computational Intelligence 2024

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

Comments 63 pages, 4 figures, published at ICML 2024

Model-based reinforcement learning for protein backbone design

Frederic Renard, Cyprien Courtot, Alfredo Reichlin, Oliver Bent

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.AI

Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control

Minjun Sung, Sambhu H. Karumanchi, Aditya Gahlawat, Naira Hovakimyan

专题命中 模型式强化学习 ：model based reinforcement learning(title)；model-based reinforcement learning(abstract)；分类 cs.LG

Unsupervised Learning of Hybrid Latent Dynamics: A Learn-to-Identify Framework

Yubo Ye, Sumeet Vadhavkar, Xiajun Jiang, Ryan Missel, Huafeng Liu, Linwei Wang

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

Comments Under Review

Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models

Yule Wang, Zijing Wu, Chengrui Li, Anqi Wu

专题命中 模型式强化学习 ：latent dynamics(title,abstract)；分类 cs.LG

A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning

Abdelhakim Benechehab, Albert Thomas, Giuseppe Paolo, Maurizio Filippone, Balázs Kégl

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning

Maria Rigaki, Sebastian Garcia

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.AI

Comments 12 pages, 3 figures, 3 tables. Accepted at ESORICS 2023

An Analysis of Model-Based Reinforcement Learning From Abstracted Observations

Rolf A. N. Starre, Marco Loog, Elena Congeduti, Frans A. Oliehoek

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.LG

Comments 36 pages, 2 figures, published in Transactions on Machine Learning Research (TMLR) 2023

Learning to Shape by Grinding: Cutting-surface-aware Model-based Reinforcement Learning

Takumi Hachimine, Jun Morimoto, Takamitsu Matsubara

专题命中 模型式强化学习 ：model-based reinforcement learning(title,abstract)；分类 cs.RO

Comments 8 pages, Accepted by Robotics and Automation Letters