世界模型 - arXivDaily 专题

2210.11259 2022-10-21 cs.LG cs.AI cs.FL cs.RO 60%

Safe Policy Improvement in Constrained Markov Decision Processes

Luigi Berducci, Radu Grosu

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

Comments Accepted for presentation at the International Symposium on Leveraging Applications of Formal Methods (ISoLA, 2022)

Journal ref LNCS 13701 (2022) 360-381;

2203.04955 2022-07-21 cs.LG cs.RO 60%

Temporal Difference Learning for Model Predictive Control

Nicklas Hansen, Xiaolong Wang, Hao Su

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

Comments Code and videos: https://nicklashansen.github.io/td-mpc

2111.07395 2022-06-24 cs.LG cs.AI cs.RO 60%

Explicit Explore, Exploit, or Escape ($E^4$): near-optimal safety-constrained reinforcement learning in polynomial time

David M. Bossens, Nicholas Bishop

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

Comments Accepted at Machine Learning

2110.05415 2022-06-24 eess.SY cs.AI cs.LG cs.RO cs.SY 60%

Safe Reinforcement Learning Using Robust Control Barrier Functions

Yousef Emam, Gennaro Notomista, Paul Glotfelter, Zsolt Kira, Magnus Egerstedt

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

Comments Submitted to IEEE Robotics and Automation Letters (RA-L)

2106.15612 2021-07-01 cs.LG cs.AI cs.RO 60%

Learning Task Informed Abstractions

Xiang Fu, Ge Yang, Pulkit Agrawal, Tommi Jaakkola

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

Comments 8 pages, 12 figures

2006.01959 2021-04-28 cs.LG cs.CV stat.ML 60%

NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spaces

Miguel Jaques, Michael Burke, Timothy Hospedales

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

2103.02084 2021-03-04 cs.LG cs.AI cs.RO 60%

Minimax Model Learning

Cameron Voloshin, Nan Jiang, Yisong Yue

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

Journal ref PMLR, Volume 130, 2021

2102.12924 2021-03-04 cs.LG cs.AI stat.ML 60%

Visualizing MuZero Models

Joery A. de Vries, Ken S. Voskuil, Thomas M. Moerland, Aske Plaat

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

2006.11441 2020-12-01 cs.LG cs.AI cs.RO stat.ML 60%

Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen, Ding Zhao

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

Comments 16 pages, 6 figures

2011.06619 2020-11-16 cs.RO cs.AI cs.LG 60%

Learning Latent Representations to Influence Multi-Agent Interaction

Annie Xie, Dylan P. Losey, Ryan Tolsma, Chelsea Finn, Dorsa Sadigh

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

Comments Conference on Robot Learning (CoRL) 2020. Supplementary website at https://sites.google.com/view/latent-strategies/

2010.09546 2020-10-29 cs.LG cs.AI stat.ML 60%

Model-based Policy Optimization with Unsupervised Model Adaptation

Jian Shen, Han Zhao, Weinan Zhang, Yong Yu

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

Comments Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020)

2007.01995 2020-09-30 cs.LG cs.AI stat.ML 60%

Bidirectional Model-based Policy Optimization

Hang Lai, Jian Shen, Weinan Zhang, Yong Yu

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

Comments Accepted at ICML2020

2002.01587 2020-06-08 cs.RO cs.LG cs.SY eess.SY math.OC 60%

Deep Learning Tubes for Tube MPC

David D. Fan, Ali-akbar Agha-mohammadi, Evangelos A. Theodorou

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

Comments RSS 2020 Camera Ready Version

1912.03015 2020-06-08 cs.LG cs.RO stat.ML 60%

Learning to Correspond Dynamical Systems

Nam Hee Kim, Zhaoming Xie, Michiel van de Panne

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

2005.13778 2020-05-29 cs.LG cs.AI stat.ML 60%

Domain Knowledge Integration By Gradient Matching For Sample-Efficient Reinforcement Learning

Parth Chadha

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

2001.07527 2020-01-22 cs.LG cs.AI cs.MA stat.ML 60%

Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping

Eugenio Bargiacchi, Timothy Verstraeten, Diederik M. Roijers, Ann Nowé

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

1911.12553 2019-12-02 cs.LG cs.AI cs.RO 60%

Augmented Random Search for Quadcopter Control: An alternative to Reinforcement Learning

Ashutosh Kumar Tiwari, Sandeep Varma Nadimpalli

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

Comments 10 pages. 11 figures, Published in International Journal of Information Technology and Computer Science(IJITCS), http://www.mecs-press.org/ijitcs

Journal ref IJITCS Vol. 11, No. 11, Nov. 2019 , Page Range. 24-33

1910.13399 2019-10-30 cs.RO cs.AI cs.LG 60%

Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization

Matteo Turchetta, Andreas Krause, Sebastian Trimpe

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

Comments Submitted to IEEE Conference on Robotics and Automation 2020 (ICRA)

1908.06012 2019-08-19 cs.LG cs.AI stat.ML 60%

Model-based Lookahead Reinforcement Learning

Zhang-Wei Hong, Joni Pajarinen, Jan Peters

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

1803.11347 2019-03-01 cs.LG cs.RO stat.ML 60%

Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

Anusha Nagabandi, Ignasi Clavera, Simin Liu, Ronald S. Fearing, Pieter Abbeel, Sergey Levine, Chelsea Finn

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

Comments First 2 authors contributed equally. Website: https://sites.google.com/berkeley.edu/metaadaptivecontrol

1902.01240 2019-02-06 cs.LG cs.AI cs.RO stat.ML 60%

PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos

Paavo Parmas, Carl Edward Rasmussen, Jan Peters, Kenji Doya

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

Comments ICML 2018

1802.10592 2018-10-08 cs.LG cs.AI cs.RO 60%

Model-Ensemble Trust-Region Policy Optimization

Thanard Kurutach, Ignasi Clavera, Yan Duan, Aviv Tamar, Pieter Abbeel

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

1707.03497 2017-11-08 cs.AI cs.LG 60%

Value Prediction Network

Junhyuk Oh, Satinder Singh, Honglak Lee

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

Comments NIPS 2017

1412.6451 2014-12-22 cs.LG cs.AI cs.RO 60%

Grounding Hierarchical Reinforcement Learning Models for Knowledge Transfer

Mark Wernsdorfer, Ute Schmid

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

Comments 14 pages, 4 figures

1304.2024 2014-03-18 cs.LG cs.AI cs.MA stat.ML 60%

A General Framework for Interacting Bayes-Optimally with Self-Interested Agents using Arbitrary Parametric Model and Model Prior

Trong Nghia Hoang, Kian Hsiang Low

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

Comments 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), Extended version with proofs, 10 pages

1711.05008 2017-11-15 cond-mat.mtrl-sci 59%

Cluster dynamics modeling of Mn-Ni-Si precipitates in ferritic-martensitic steel under irradiation

Jia-Hong Ke, Huibin Ke, G. Robert Odette, Dane Morgan

专题命中模型式强化学习：dynamics model(title,abstract)；predictive model(abstract)；predictive models(abstract)

Journal ref Cluster dynamics modeling of Mn-Ni-Si precipitates in ferritic-martensitic steel under irradiation, J. Nucl. Mater. 498 (2018) 83-88

2608.11349 2026-08-13 cs.LG cs.AI 新提交 58%

Dynamics Models for Offline Hyperparameter Selection in Real-World RL

面向真实世界强化学习的离线超参数选择的动力学模型

Jordan Coblin, Han Wang, Martha White, Adam White

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

AI总结本文将校准模型首次应用于市政水处理厂的真实RL场景，评估其在高维非平稳传感器数据上的表现，为离线动力学模型支持真实RL部署提供概念验证。

Comments Accepted to the 2026 Reinforcement Learning Conference (RLC)

2607.20939 2026-08-04 eess.SY cs.AI cs.RO cs.SY 版本更新 58%

Interaction Dynamics Modeling and Predictive Control for Safe Steerable Catheter--Tissue Interaction

用于安全可控导管-组织相互作用的相互作用动力学建模与预测控制

Yongyan Cao

机构 * Voryx Robotic LLC

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

AI总结研究安全可控导管-组织相互作用动力学问题，通过建立模型、采用部分物理前馈、预测优化器及增强卡尔曼滤波器等方法，实现无偏移运动调节与接触力安全，模拟结果验证了方法有效性，硬件验证待开展。

2606.23436 2026-06-23 cs.CV cs.AI cs.LG 新提交 58%

Rethinking Object-Centric Representations for Video Dynamics Modeling

重新思考面向对象的视频动态建模表示

Amaury Wei, Ismail Nejjar, Olga Fink

机构 * Intelligent Maintenance and Operation Systems (IMOS) École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院智能维护与操作系统实验室（IMOS））

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

AI总结提出STAITUS框架，通过解耦每个槽为外观和几何位姿，在运动、遮挡等场景下实现更清晰的分割和更稳定的身份保持。

Comments 17 pages, 6 figures

2603.23977 2026-06-01 cs.LG cs.AI 58%

Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE Solving and Visual Perception

电路启发的具有统一神经动力学建模的高阶神经网络用于PDE求解与视觉感知

Tongfei Chen, Jingying Yang, Linlin Yang, Juan Zhang, Jinhu Lü, David Doermann, Chunyu Xie, Long He, Tian Wang, Guodong Guo, Baochang Zhang

机构 * Communication University of China（通信大学）； AI Research, Qihoo 360（360人工智能研究院，奇虎360）； Eastern Institute of Technology, Ningbo（宁波工程技术院）

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

AI总结提出电路启发的高阶神经网络（CHONN），通过基尔霍夫级联组合实现高阶动力学算子，在PDE求解、长期物理预测和ImageNet-1K识别中提升结构保真度和稳定性。

1. 模型式强化学习 1126 篇

Safe Policy Improvement in Constrained Markov Decision Processes

Temporal Difference Learning for Model Predictive Control

Explicit Explore, Exploit, or Escape ($E^4$): near-optimal safety-constrained reinforcement learning in polynomial time

Safe Reinforcement Learning Using Robust Control Barrier Functions

Learning Task Informed Abstractions

NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spaces

Minimax Model Learning

Visualizing MuZero Models

Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

Learning Latent Representations to Influence Multi-Agent Interaction

Model-based Policy Optimization with Unsupervised Model Adaptation

Bidirectional Model-based Policy Optimization

Deep Learning Tubes for Tube MPC

Learning to Correspond Dynamical Systems

Domain Knowledge Integration By Gradient Matching For Sample-Efficient Reinforcement Learning

Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping

Augmented Random Search for Quadcopter Control: An alternative to Reinforcement Learning

Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization

Model-based Lookahead Reinforcement Learning

Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos

Model-Ensemble Trust-Region Policy Optimization

Value Prediction Network

Grounding Hierarchical Reinforcement Learning Models for Knowledge Transfer

A General Framework for Interacting Bayes-Optimally with Self-Interested Agents using Arbitrary Parametric Model and Model Prior

Cluster dynamics modeling of Mn-Ni-Si precipitates in ferritic-martensitic steel under irradiation

Dynamics Models for Offline Hyperparameter Selection in Real-World RL

Interaction Dynamics Modeling and Predictive Control for Safe Steerable Catheter--Tissue Interaction

Rethinking Object-Centric Representations for Video Dynamics Modeling

Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE Solving and Visual Perception