世界模型

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)

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/

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

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

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/

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)

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)

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

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

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

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

Objective Mismatch in Model-based Reinforcement Learning

Nathan Lambert, Brandon Amos, Omry Yadan, Roberto Calandra

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)

Comments 9 pages, 2 pages references, 5 pages appendices

Journal ref Proceedings of the 2nd Conference on Learning for Dynamics and Control, PMLR 120:761-770, 2020

Discriminator Augmented Model-Based Reinforcement Learning

Behzad Haghgoo, Allan Zhou, Archit Sharma, Chelsea Finn

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)

A Game Theoretic Framework for Model Based Reinforcement Learning

Aravind Rajeswaran, Igor Mordatch, Vikash Kumar

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、cs.RO

Comments ICML 2020. This version contains expanded discussion, hyperparameter configurations, and ablation studies

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra

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 19 pages, accepted by AISTATS 2021

Learning to Fly via Deep Model-Based Reinforcement Learning

Philip Becker-Ehmck, Maximilian Karl, Jan Peters, Patrick van der Smagt

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

Modeling Survival in model-based Reinforcement Learning

Saeed Moazami, Peggy Doerschuk

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

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning

Nathan O. Lambert, Daniel S. Drew, Joseph Yaconelli, Roberto Calandra, Sergey Levine, Kristofer S. J. Pister

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)

Comments Accepted to IROS and RA-L, 2019. For more information, see the website: https://sites.google.com/berkeley.edu/mbrl-quadrotor/. 9 pages, 12 figures

Learning Latent Dynamics for Planning from Pixels

Danijar Hafner, Timothy Lillicrap, Ian Fischer, Ruben Villegas, David Ha, Honglak Lee, James Davidson

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

Comments 20 pages, 12 figures, 1 table

Model-Based Reinforcement Learning via Meta-Policy Optimization

Ignasi Clavera, Jonas Rothfuss, John Schulman, Yasuhiro Fujita, Tamim Asfour, 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；dynamics model(abstract)

Comments First 2 authors contributed equally. Accepted for Conference on Robot Learning (CoRL)

Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning

Juan Camilo Gamboa Higuera, David Meger, Gregory Dudek

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.RO；dynamics model(abstract)

Comments 8 pages, 7 figures

Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration

Christopher Xie, Sachin Patil, Teodor Moldovan, Sergey Levine, Pieter Abbeel

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)

Comments 8 pages

A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control

Todd Hester, Michael Quinlan, Peter Stone

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

Comments Added a reference Presents a real-time parallel architecture for model-based reinforcement learning methods

Learning Robust Controllers Via Probabilistic Model-Based Policy Search

Valentin Charvet, Bjørn Sand Jensen, Roderick Murray-Smith

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

Comments Accepted at RobustML Workshop - ICLR 2021

LD4WAM: Learning Latent Dynamics from Human Videos for World Action Models

LD4WAM：从人类视频学习世界动作模型的潜在动力学

Zhenhao Shen, Jiaqi Liang, Jasper Lu, Feng Jiang, Yuran Wang, Chuanbo Wei, Jiayi Liu, Jianchun Yang, Qize Yu, Jiadi You, Ce Hao, Guanqi He, Chen Xie, Ruihai Wu

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

AI总结 LD4WAM通过运动对齐的潜在动力学，结合语义重建与真实运动对齐训练的潜在动力学模型和MoT架构的世界动力学动作模型，在RoboTwin仿真及真实机器人上表现良好，可泛化到未见物体与背景。

Self-Curriculum Model-based Reinforcement Learning for Shape Control of Deformable Linear Objects

基于自课程模型的可变形线性物体形状控制强化学习

Zhaowei Liang, Song Wang, Zhao Jin, Shirui Wu, Dan Wu

机构 * Department of Mechanical Engineering, Tsinghua University（清华大学机械工程系） 纠错

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

AI总结 提出两阶段框架，结合基于模型强化学习与在线视觉伺服，通过自课程目标生成机制实现可变形线性物体高效精确的形状控制，在仿真和真实任务中优于主流方法。

Comments Accepted to IROS 2026

Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes

离散动作非马尔可夫奖励决策过程中基于模型的强化学习

Alessandro Trapasso, Luca Iocchi, Fabio Patrizi

机构 * Fondazione Bruno Kessler（布雷诺·科塞拉基金会） ； Sapienza University of Rome（罗马萨皮恩扎大学） 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.AI、cs.LG

AI总结 提出QR-MAX算法，通过奖励机分解马尔可夫转移学习与非马尔可夫奖励处理，首次在离散NMRDP中获得PAC收敛到ε-最优策略的多项式样本复杂度，并扩展至连续状态空间。

Comments Accepted at IJCAI-ECAI 2026. 19 pages, 32 figures, includes appendix

Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics

通过潜在动力学统一无模型效率与基于模型的表示

Jashaswimalya Acharjee, Balaraman Ravindran

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

AI总结 提出统一潜在动力学算法，通过将状态-动作对嵌入到值函数近似线性的潜在空间，无需规划开销即可融合无模型效率与基于模型表示的优势，在80个环境中匹配或超越专门基线。

Comments Similarities found with a prior work. Hence, requesting for withdrawal until further notice

Post-Hoc Robustness for Model-Based Reinforcement Learning

基于模型的强化学习的后验鲁棒性

Siemen Herremans, Ali Anwar, Siegfried Mercelis

机构 * Carnegie Mellon University（卡内基梅隆大学） 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.AI、cs.LG

AI总结 提出一种在推理时利用学习模型和名义策略进行鲁棒策略改进的后验鲁棒化方法，通过对抗性展开的模型预测控制提升鲁棒性，无需额外训练神经网络。

Focal plane wavefront control with model-based reinforcement learning

基于模型的强化学习进行焦平面波前控制

Jalo Nousiainen, Iremsu Taskin, Markus Kasper, Gilles Orban De Xivry, Olivier Absil

机构 * European Southern Observatory (ESO)（欧洲南天文学观测站） ； STAR Institute, Université de Liège（利根大学STAR研究所） 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、cs.RO

AI总结 提出基于模型的强化学习算法PO4NCPA，通过顺序相位分集自动校正动态和静态非共路像差，实现高对比度成像中的焦平面波前控制。

Comments 13 pages, 11 figures accepted by A&A

Journal ref A&A 709, A267 (2026)