世界模型 - arXivDaily 专题

2108.11645 2021-10-20 cs.AI 78%

Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control

Wanpeng Zhang, Xiaoyan Cao, Yao Yao, Zhicheng An, Xi Xiao, Dijun Luo

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

2107.07410 2021-07-16 cs.LG 78%

PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration

Yuda Song, Wen Sun

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

2102.09850 2021-06-08 cs.LG cs.AI cs.RO 78%

Model-Invariant State Abstractions for Model-Based Reinforcement Learning

Manan Tomar, Amy Zhang, Roberto Calandra, Matthew E. Taylor, Joelle Pineau

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

2103.14407 2021-04-14 cs.LG 78%

Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow

John McLeod, Hrvoje Stojic, Vincent Adam, Dongho Kim, Jordi Grau-Moya, Peter Vrancx, Felix Leibfried

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

2006.01107 2020-06-02 cs.LG stat.ML 78%

Model-Based Reinforcement Learning with Value-Targeted Regression

Alex Ayoub, Zeyu Jia, Csaba Szepesvari, Mengdi Wang, Lin F. Yang

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

1910.12453 2019-10-29 cs.LG cs.AI cs.RO stat.ML 78%

Asynchronous Methods for Model-Based Reinforcement Learning

Yunzhi Zhang, Ignasi Clavera, Boren Tsai, Pieter Abbeel

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

Comments 10 pages, CoRL 2019

1904.06786 2019-10-09 cs.RO cs.AI cs.LG 78%

Curious iLQR: Resolving Uncertainty in Model-based RL

Sarah Bechtle, Yixin Lin, Akshara Rai, Ludovic Righetti, Franziska Meier

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

2607.01986 2026-07-03 cs.LG cs.CV 新提交 78%

Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling

液态潜在状态动力学用于可解释的涡扇退化建模

Weizhi Nie, Weijie Wang, Yuting Su

机构 * Tianjin University（天津大学）

专题命中模型式强化学习：world model(abstract)；world model(abstract)；latent dynamics(abstract)；分类 cs.LG、cs.CV

AI总结提出液态神经网络作为潜在动力学模型，通过分解潜在状态为退化与工况分量，在C-MAPSS上实现可解释的退化建模，传感器预测RMSE从0.2438降至0.2266。

Comments Preprint. 37 references, 8 figures

2510.22969 2025-12-02 cs.AI cs.MA 78%

Multi-Agent Conditional Diffusion Model with Mean Field Communication as Wireless Resource Allocation Planner

多智能体条件扩散模型与均场通信作为无线资源分配规划器

Kechen Meng, Sinuo Zhang, Rongpeng Li, Xiangming Meng, Yansha Deng, Chan Wang, Ming Lei, Zhifeng Zhao

机构 * College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）； Zhejiang University-University of Illinois Urbana-Champaign (ZJU-UIUC) Institute, Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所）； Department of Engineering, King’s College London（伦敦国王学院工程系）

专题命中模型式强化学习：world model(abstract)；world model(abstract)；model-based RL(abstract)；分类 cs.AI、cs.MA

AI总结多智能体条件扩散模型与均场通信用于无线资源分配规划，通过扩散模型和逆动态模型提升样本效率与策略可扩展性，理论保证收敛稳定性，实验显示在无线网络优化中表现优异。

2604.27450 2026-05-01 cs.RO cs.AI 77%

RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC

RAY-TOLD: 基于射线的任务导向潜在动力学用于密集动态障碍物避障与TDMPC

Seungho Han, Seokju Lee, Jeonguk Kang

机构 * School of Electrical Engineering, Hanyang University（翰阳大学电气工程学院）； Mechatronics, Systems and Control Lab (MSC Lab), Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST)（机械工程系，韩国科学技术院（KAIST）机电系统与控制实验室（MSC实验室））； Samsung Research, Samsung Electronics（三星研究所，三星电子）

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

AI总结本文提出RAY-TOLD，结合物理基础MPPI的鲁棒性与强化学习的长视界，通过LiDAR中心的潜在动力学模型实现动态障碍物避障，提升导航可靠性与安全性。

Comments 8 pages, 4 figures

2604.04401 2026-04-07 cs.RO cs.LG cs.SY eess.SY 77%

ReinVBC: A Model-based Reinforcement Learning Approach to Vehicle Braking Controller

ReinVBC：一种基于模型的强化学习方法用于车辆制动控制器

Haoxin Lin, Junjie Zhou, Daheng Xu, Yang Yu

机构 * National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）； School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）； Polixir Technologies（探境科技）

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

AI总结本文提出ReinVBC，利用基于模型的强化学习方法解决车辆制动控制问题，通过工程设计获得可靠的车辆动力学模型和制动策略，实验证明其在实际车辆制动中的有效性及替代传统防抱死刹车系统潜力。

2604.02260 2026-04-03 cs.LG cs.RO 77%

Model-Based Reinforcement Learning for Control under Time-Varying Dynamics

基于模型的强化学习用于时间变化动态下的控制

Klemens Iten, Bruce Lee, Chenhao Li, Lenart Treven, Andreas Krause, Bhavya Sukhija

机构 * ETH Zürich（苏黎世联邦理工学院）； ETH AI Center（苏黎世联邦理工学院人工智能中心）

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

AI总结本文研究了在时间变化动态下基于模型的强化学习控制，通过高斯过程动态模型分析，提出适应性数据缓冲机制的算法，提升了非平稳动态连续控制任务的性能。

Comments 15 pages, 5 figues, 2 tables. This work has been submitted to the IEEE for possible publication

2603.15857 2026-03-18 cs.AI cs.LG cs.RO 77%

Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models

正则化潜在动态预测是行为基础模型的强基线

Pranaya Jajoo, Harshit Sikchi, Siddhant Agarwal, Amy Zhang, Scott Niekum, Martha White

机构 * Department of Computing Science, University of Alberta, Canada（阿尔伯塔大学计算机科学系）； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所）； Canada CIFAR AI Chair（加拿大CIFAR人工智能 chair）； The University of Texas at Austin（德克萨斯大学奥斯汀分校）； University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校）

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

AI总结本文探讨零样本强化学习中复杂表征学习目标的必要性，提出正则化潜在动态预测方法，通过正则化保持特征多样性，优于现有方法，并在低覆盖场景中表现优异。

Comments ICLR 2026

2510.05558 2025-10-08 cs.CV cs.LG 77%

Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics

Christopher Hoang, Mengye Ren

机构 * New York University（纽约大学）

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

Comments Project page: https://agenticlearning.ai/midway-network/

2509.12531 2025-09-17 cs.RO cs.AI cs.LG cs.SY eess.SY 77%

Pre-trained Visual Representations Generalize Where it Matters in Model-Based Reinforcement Learning

Scott Jones, Liyou Zhou, Sebastian W. Pattinson

机构 * Institute for Manufacturing, Department of Engineering, University of Cambridge（剑桥大学制造研究所、工程系）

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

2507.09534 2025-07-15 cs.AI cs.LG cs.RO 77%

Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement Learning

Guanquan Wang, Takuya Hiraoka, Yoshimasa Tsuruoka

机构 * Department of Information and Communication Engineering（信息与通信工程系）； The University of Tokyo（东京大学）； NEC Corporation（日本电装公司）

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

2502.10077 2025-02-17 cs.AI cs.LG 77%

Towards Empowerment Gain through Causal Structure Learning in Model-Based RL

Hongye Cao, Fan Feng, Meng Fang, Shaokang Dong, Tianpei Yang, Jing Huo, Yang Gao

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

2408.10713 2024-08-21 cs.LG cs.AI 77%

Offline Model-Based Reinforcement Learning with Anti-Exploration

Padmanaba Srinivasan, William Knottenbelt

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

2105.05716 2024-07-31 cs.AI cs.LG 77%

Acting upon Imagination: when to trust imagined trajectories in model based reinforcement learning

Adrian Remonda, Eduardo Veas, Granit Luzhnica

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

2404.03037 2024-05-27 cs.LG cs.AI 77%

Model-based Reinforcement Learning for Parameterized Action Spaces

Renhao Zhang, Haotian Fu, Yilin Miao, George Konidaris

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

2311.01450 2024-02-20 cs.LG cs.AI cs.RO 77%

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing

Vint Lee, Pieter Abbeel, Youngwoon Lee

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

Comments For code and website, see https://vint-1.github.io/dreamsmooth/

2309.00082 2023-10-26 cs.LG cs.AI cs.RO 77%

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

Chuning Zhu, Max Simchowitz, Siri Gadipudi, Abhishek Gupta

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

2309.05582 2023-09-12 cs.LG cs.AI cs.RO 77%

Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning

Marin Vlastelica, Sebastian Blaes, Cristina Pineri, Georg Martius

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

2209.08466 2023-06-27 cs.LG cs.AI cs.RO 77%

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective

Raj Ghugare, Homanga Bharadhwaj, Benjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov

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

Comments ICLR 2023, Project website with code: https://alignedlatentmodels.github.io/

2306.12077 2023-06-22 cs.LG cs.AI 77%

Learning Latent Dynamics via Invariant Decomposition and (Spatio-)Temporal Transformers

Kai Lagemann, Christian Lagemann, Sach Mukherjee

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

2212.02179 2023-05-16 cs.LG cs.RO 77%

Physics-Informed Model-Based Reinforcement Learning

Adithya Ramesh, Balaraman Ravindran

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

2109.10312 2022-09-20 cs.RO cs.AI cs.LG 77%

Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks

Bohan Wu, Suraj Nair, Li Fei-Fei, Chelsea Finn

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

Comments Equal advising and contribution for last two authors

2008.08157 2022-07-12 cs.RO cs.LG cs.SY eess.SY 77%

Heteroscedastic Uncertainty for Robust Generative Latent Dynamics

Oliver Limoyo, Bryan Chan, Filip Marić, Brandon Wagstaff, Rupam Mahmood, Jonathan Kelly

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

Comments In IEEE Robotics and Automation Letters (RA-L) and presented at the IEEE International Conference on Intelligent Robots and Systems (IROS'20), Las Vegas, USA, October 25-29, 2020

Journal ref IEEE Robotics and Automation Letters (RA-L), Vol. 5, No. 4, pp. 6654-6661, Oct. 2020

2110.04135 2022-03-17 cs.LG cs.AI 77%

Revisiting Design Choices in Offline Model-Based Reinforcement Learning

Cong Lu, Philip J. Ball, Jack Parker-Holder, Michael A. Osborne, Stephen J. Roberts

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

Comments Spotlight @ ICLR 2022; Spotlight @ RL4RealLife Workshop ICML2021

2112.05244 2022-03-16 cs.LG cs.AI cs.IT cs.RO math.IT stat.ML 77%

An Experimental Design Perspective on Model-Based Reinforcement Learning

Viraj Mehta, Biswajit Paria, Jeff Schneider, Stefano Ermon, Willie Neiswanger

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

Comments Conference paper at ICLR 2022

1. 模型式强化学习 1124 篇

Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control

PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration

Model-Invariant State Abstractions for Model-Based Reinforcement Learning

Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow

Model-Based Reinforcement Learning with Value-Targeted Regression

Asynchronous Methods for Model-Based Reinforcement Learning

Curious iLQR: Resolving Uncertainty in Model-based RL

Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling

Multi-Agent Conditional Diffusion Model with Mean Field Communication as Wireless Resource Allocation Planner

RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC

ReinVBC: A Model-based Reinforcement Learning Approach to Vehicle Braking Controller

Model-Based Reinforcement Learning for Control under Time-Varying Dynamics

Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models

Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics

Pre-trained Visual Representations Generalize Where it Matters in Model-Based Reinforcement Learning

Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement Learning

Towards Empowerment Gain through Causal Structure Learning in Model-Based RL

Offline Model-Based Reinforcement Learning with Anti-Exploration

Acting upon Imagination: when to trust imagined trajectories in model based reinforcement learning

Model-based Reinforcement Learning for Parameterized Action Spaces

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective

Learning Latent Dynamics via Invariant Decomposition and (Spatio-)Temporal Transformers

Physics-Informed Model-Based Reinforcement Learning

Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks

Heteroscedastic Uncertainty for Robust Generative Latent Dynamics

Revisiting Design Choices in Offline Model-Based Reinforcement Learning

An Experimental Design Perspective on Model-Based Reinforcement Learning