世界模型 - arXivDaily 专题

2201.03116 2022-01-27 eess.SY cs.LG cs.SY 74%

Opportunities of Hybrid Model-based Reinforcement Learning for Cell Therapy Manufacturing Process Control

Hua Zheng, Wei Xie, Keqi Wang, Zheng Li

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

Comments 14 pages, 2 figures

2105.13524 2022-01-19 cs.LG 74%

Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture

Suyoung Lee, Sae-Young Chung

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

Comments NeurIPS 2021

2112.07746 2021-12-16 cs.LG cs.SY eess.SY math.OC stat.ML 74%

CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learning

Kevin Huang, Sahin Lale, Ugo Rosolia, Yuanyuan Shi, Anima Anandkumar

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

2006.11911 2021-12-07 cs.LG stat.ML 74%

Towards Tractable Optimism in Model-Based Reinforcement Learning

Aldo Pacchiano, Philip J. Ball, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts

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

Comments Presented as a conference paper at UAI 2021

2110.05556 2021-10-13 cs.RO cs.SY eess.SY 74%

Addressing crash-imminent situations caused by human driven vehicle errors in a mixed traffic stream: a model-based reinforcement learning approach for CAV

Jiqian Dong, Sikai Chen, Samuel Labi

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

Comments Under review for presentation at TRB 2022 Annual Meeting

2107.00848 2021-07-05 stat.ML cs.LG 74%

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

Nan Rosemary Ke, Aniket Didolkar, Sarthak Mittal, Anirudh Goyal, Guillaume Lajoie, Stefan Bauer, Danilo Rezende, Yoshua Bengio, Michael Mozer, Christopher Pal

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

2102.04764 2021-06-14 cs.LG stat.ML 74%

Continuous-Time Model-Based Reinforcement Learning

Çağatay Yıldız, Markus Heinonen, Harri Lähdesmäki

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

2104.10159 2021-04-21 cs.AI cs.SY eess.SY 74%

MBRL-Lib: A Modular Library for Model-based Reinforcement Learning

Luis Pineda, Brandon Amos, Amy Zhang, Nathan O. Lambert, Roberto Calandra

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

2103.06807 2021-03-12 cs.HC cs.AI 74%

Adapting User Interfaces with Model-based Reinforcement Learning

Kashyap Todi, Gilles Bailly, Luis A. Leiva, Antti Oulasvirta

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

Comments 13 pages, 10 figures, ACM CHI 2021 Full Paper

2009.01221 2021-01-13 cs.RO 74%

Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Nathan Lambert, Craig Schindler, Daniel Drew, Kristofer Pister

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

Comments 7 pages, 1 page appendix

Journal ref IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 455-461, April 2021

2006.16210 2020-10-27 cs.LG stat.ML 74%

Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs

Jianzhun Du, Joseph Futoma, Finale Doshi-Velez

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

Comments NeurIPS 2020, 20 pages, 7 figures

2010.06266 2020-10-14 cs.LG 74%

Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control

Taku Yamagata, Aisling O'Kane, Amid Ayobi, Dmitri Katz, Katarzyna Stawarz, Paul Marshall, Peter Flach, Raúl Santos-Rodríguez

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

Comments Presented at ECAI 2020 SP4HC Workshop

1911.03845 2020-01-22 cs.LG cs.IR stat.ML 74%

Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation

Xueying Bai, Jian Guan, Hongning Wang

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

1904.10090 2020-01-16 cs.LG stat.ML 74%

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version

Erwan Lecarpentier, Emmanuel Rachelson

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

Comments Published at NeurIPS 2019, 17 pages, 3 figures

Journal ref year: 2019; page range: 7214--7223

1912.11206 2019-12-25 cs.LG stat.ML 74%

Learning to Combat Compounding-Error in Model-Based Reinforcement Learning

Chenjun Xiao, Yifan Wu, Chen Ma, Dale Schuurmans, Martin Müller

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

1911.12574 2019-12-02 cs.LG stat.ML 74%

Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization

Qi Zhou, Houqiang Li, Jie Wang

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

1910.03743 2019-10-10 cs.AI 74%

Model-based Reinforcement Learning for Predictions and Control for Limit Order Books

Haoran Wei, Yuanbo Wang, Lidia Mangu, Keith Decker

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

1907.11971 2019-07-30 cs.AI 74%

Towards Model-based Reinforcement Learning for Industry-near Environments

Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

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

1811.08540 2019-05-31 cs.LG stat.ML 74%

Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches

Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford

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

Comments COLT 2019

1806.00175 2018-11-27 cs.AI 74%

Fast Exploration with Simplified Models and Approximately Optimistic Planning in Model Based Reinforcement Learning

Ramtin Keramati, Jay Whang, Patrick Cho, Emma Brunskill

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

1705.00470 2017-08-09 stat.ML cs.LG 74%

Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning

Thomas M. Moerland, Joost Broekens, Catholijn M. Jonker

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

Comments Scaling Up Reinforcement Learning (SURL) Workshop @ European Machine Learning Conference (ECML)

1406.1853 2014-11-04 stat.ML cs.LG 74%

Model-based Reinforcement Learning and the Eluder Dimension

Ian Osband, Benjamin Van Roy

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

2408.17380 2026-01-19 cs.AI cs.LG 73%

Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control

交通专家与残差强化学习相遇：基于知识的模型驱动残差强化学习用于智能交通车辆轨迹控制

Zihao Sheng, Zilin Huang, Sikai Chen

机构 * Department of Civil and Environmental Engineering, University of Wisconsin-Madison, Madison, WI, 53706, USA（土木与环境工程系，威斯尼大学麦迪逊分校）

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

AI总结本文提出基于知识的模型驱动残差强化学习框架，用于智能交通车辆轨迹控制，结合交通专家知识与传统控制方法，提升学习效率与交通流平滑度。

Comments Accepted by Communications in Transportation Research

Journal ref Communications in Transportation Research 4 (2024): 100142

2204.10419 2023-01-23 cs.LG cs.AI cs.CV cs.RO 73%

Learning Sequential Latent Variable Models from Multimodal Time Series Data

Oliver Limoyo, Trevor Ablett, Jonathan Kelly

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

Comments In: Petrovic, I., Menegatti, E., Marković, I. (eds) Intelligent Autonomous Systems 17. IAS 2022. Lecture Notes in Networks and Systems, vol 577. Springer, Cham

2606.24507 2026-06-24 quant-ph 新提交 72%

Uncovering Latent Structures in Robust Pulse Sequences: A Model-Based Reinforcement Learning Approach for Adaptable Quantum Control

揭示鲁棒脉冲序列中的潜在结构：一种基于模型的强化学习方法用于自适应量子控制

Tobias Kiermeyer, Thomas Heydenreich, Léo Van Damme, Sebastian Hohenemser, Florian Marquardt, Steffen J. Glaser

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

AI总结提出一种基于模型强化学习的鲁棒最优量子控制方法，通过将哈密顿量嵌入训练管道的神经网络，无需预计算数据即可为整个门族生成鲁棒脉冲，在单自旋系统上实现毫秒级任意旋转角脉冲，保真度媲美多种子GRAPE，并发现控制景观中的结构化相位轮廓。

Comments 14 pages, 8 figures

1702.08584 2026-06-04 eess.SY cs.SY math.OC 72%

Model-based reinforcement learning in differential graphical games

基于微分图游戏的模型引导强化学习

Rushikesh Kamalapurkar, Justin R. Klotz, Patrick Walters, Warren E. Dixon

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

AI总结本文结合微分博弈理论与actor-critic-identifier架构，提出连续控制策略以实现多智能体系统编队跟踪，通过通信拓扑中的扩展邻居反馈设计近似最优控制器，仿真验证了该方法的有效性。

1506.00685 2026-06-04 eess.SY cs.SY math.OC 72%

Model-based reinforcement learning for infinite-horizon approximate optimal tracking

基于模型的强化学习用于无限 horizon 近似最优跟踪

Rushikesh Kamalapurkar, Lindsey Andrews, Patrick Walters, Warren E. Dixon

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

AI总结本文提出了一种近似在线自适应解决方案，用于解决具有未知漂移动力学的连续时间非线性系统的无限 horizon 最优跟踪问题，通过基于模型的强化学习放松持续激励条件，并通过Lyapunov稳定性分析证明了策略收敛性。

1509.01186 2026-06-04 eess.SY cs.SY 72%

Model Based Reinforcement Learning with Final Time Horizon Optimization

基于最终时间 horizon 的模型驱动强化学习

Wei Sun, Evangelos Theodorou, Panagiotis Tsiotras

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

AI总结本文提出一种基于模型的强化学习与轨迹优化算法，通过最优控制理论和动态规划推导出反向微分方程，提供最优控制策略和时间 horizon。在低维线性问题中恢复理论最优解，并在非线性系统中验证应用效果。

Comments 9 pages, 5 figures, NIPS2015

2605.01463 2026-05-05 math.NA cs.NA 72%

A Neural Latent Dynamics Approach for Solving Inverse Problems in Cardiac Electrophysiology

用于心脏电生理学逆问题的神经潜在动态方法

Edoardo Centofanti, Giovanni Ziarelli, Simone Scacchi, Luca Franco Pavarino

专题命中模型式强化学习：latent dynamics(title,abstract)

AI总结本文提出利用潜在动态网络构建高效代理模型，解决心脏电生理学逆问题中的参数恢复难题，通过神经微分方程实现低维参数到ECG信号的映射，减少计算负担并提升临床应用效率。

Comments 29 pages, 9 figures

2602.03166 2026-02-04 math.NA cs.NA 72%

Event-Level Probabilistic Prediction of Extreme Rainfall over India Using Physics-Gated Latent Dynamics

基于物理门控隐动态的印度极端降雨事件级概率预测

Arun Govind Neelan

专题命中模型式强化学习：latent dynamics(title,abstract)

AI总结本研究提出物理门控隐动态框架，用于印度极端降雨事件的事件级概率预测，通过改进模型在极端事件检测和预测中的性能。

1. 模型式强化学习 1126 篇

Opportunities of Hybrid Model-based Reinforcement Learning for Cell Therapy Manufacturing Process Control

Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture

CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learning

Towards Tractable Optimism in Model-Based Reinforcement Learning

Addressing crash-imminent situations caused by human driven vehicle errors in a mixed traffic stream: a model-based reinforcement learning approach for CAV

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

Continuous-Time Model-Based Reinforcement Learning

MBRL-Lib: A Modular Library for Model-based Reinforcement Learning

Adapting User Interfaces with Model-based Reinforcement Learning

Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs

Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control

Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version

Learning to Combat Compounding-Error in Model-Based Reinforcement Learning

Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization

Model-based Reinforcement Learning for Predictions and Control for Limit Order Books

Towards Model-based Reinforcement Learning for Industry-near Environments

Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches

Fast Exploration with Simplified Models and Approximately Optimistic Planning in Model Based Reinforcement Learning

Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning

Model-based Reinforcement Learning and the Eluder Dimension

Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control

Learning Sequential Latent Variable Models from Multimodal Time Series Data

Uncovering Latent Structures in Robust Pulse Sequences: A Model-Based Reinforcement Learning Approach for Adaptable Quantum Control

Model-based reinforcement learning in differential graphical games

Model-based reinforcement learning for infinite-horizon approximate optimal tracking

Model Based Reinforcement Learning with Final Time Horizon Optimization

A Neural Latent Dynamics Approach for Solving Inverse Problems in Cardiac Electrophysiology

Event-Level Probabilistic Prediction of Extreme Rainfall over India Using Physics-Gated Latent Dynamics