世界模型 - arXivDaily 专题

1707.06203 2018-02-15 cs.LG cs.AI stat.ML 67%

Imagination-Augmented Agents for Deep Reinforcement Learning

Théophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adria Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, Demis Hassabis, David Silver, Daan Wierstra

专题命中仿真与规划：environment model(abstract)；model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG

1801.02425 2018-01-09 math.OC 67%

Symmetric solutions for a partial differential elliptic equation that arises in stochastic production planning with production constraints

Dragos-Patru Covei

专题命中仿真与规划：world model(abstract)；world model(abstract)

0911.0267 2009-12-01 physics.pop-ph physics.hist-ph 67%

Science, Art and Geometrical Imagination

J. -P. Luminet

专题命中仿真与规划：world model(abstract)；world model(abstract)

Comments 22 pages, 28 figures, invited talk at the IAU Symposium 260 "The Role of Astronomy in Society and Culture", UNESCO, 19-23 January 2009, Paris, Proceedings to be published

2102.02488 2021-02-05 stat.ML cs.LG 65%

From a Point Cloud to a Simulation Model: Bayesian Segmentation and Entropy based Uncertainty Estimation for 3D Modelling

Christina Petschnigg, Markus Spitzner, Lucas Weitzendorf, Jürgen Pilz

专题命中仿真与规划：simulation model(title,abstract)；environment model(abstract)；分类 cs.LG

Comments Submitted to MDPI Entropy for Review

1705.02670 2022-11-09 cs.LG cs.AI 64%

Metacontrol for Adaptive Imagination-Based Optimization

Jessica B. Hamrick, Andrew J. Ballard, Razvan Pascanu, Oriol Vinyals, Nicolas Heess, Peter W. Battaglia

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG；predictive model(abstract)；predictive models(abstract)

Comments Published as a conference paper at ICLR 2017

2104.08543 2021-04-20 cs.AI 64%

Planning with Expectation Models for Control

Katya Kudashkina, Yi Wan, Abhishek Naik, Richard S. Sutton

专题命中仿真与规划：environment model(abstract)；model-based reinforcement learning(abstract)；分类 cs.AI

1810.06544 2019-10-02 cs.LG cs.AI cs.CV cs.RO stat.ML 64%

Deep Imitative Models for Flexible Inference, Planning, and Control

Nicholas Rhinehart, Rowan McAllister, Sergey Levine

专题命中仿真与规划：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)；predictive model(abstract)；predictive models(abstract)

1305.6129 2013-05-28 cs.LG cs.AI cs.MA cs.RO 64%

Information-Theoretic Approach to Efficient Adaptive Path Planning for Mobile Robotic Environmental Sensing

Kian Hsiang Low, John M. Dolan, Pradeep Khosla

专题命中仿真与规划：environment model(abstract)；分类 cs.AI、cs.LG、cs.RO

Comments 19th International Conference on Automated Planning and Scheduling (ICAPS 2009), Extended version with proofs, 11 pages

2601.05356 2026-01-12 cs.RO cs.AI cs.MA q-bio.QM 62%

PRISM: Protocol Refinement through Intelligent Simulation Modeling

通过智能仿真建模实现协议优化：PRISM

Brian Hsu, Priyanka V Setty, Rory M Butler, Ryan Lewis, Casey Stone, Rebecca Weinberg, Thomas Brettin, Rick Stevens, Ian Foster, Arvind Ramanathan

机构 * Argonne National Laboratory（阿贡国家实验室）

专题命中仿真与规划：simulation model(title,abstract)；分类 cs.AI、cs.RO、cs.MA

AI总结 PRISM通过智能仿真建模实现实验协议的自动化设计、验证和执行，结合语言模型代理、数字孪生验证和机器人执行，提供端到端的实验流程解决方案。

Comments 43 pages, 8 figures, submitted to RSC Digital Discovery. Equal contribution: B. Hsu, P.V. Setty, R.M. Butler. Corresponding author: A. Ramanathan

2005.05385 2024-10-30 cs.LG cs.SY eess.SY stat.ML 62%

Process Knowledge Driven Change Point Detection for Automated Calibration of Discrete Event Simulation Models Using Machine Learning

Suleyman Yildirim, Alper Ekrem Murat, Murat Yildirim, Suzan Arslanturk

专题命中仿真与规划：simulation model(title,abstract)；分类 cs.LG；predictive model(abstract)；predictive models(abstract)

Comments This work has been submitted to the IEEE for possible publication

2405.18092 2024-07-23 cs.AI cs.ET cs.MA cs.RO cs.SY eess.SY 62%

LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins

Yuchen Xia, Daniel Dittler, Nasser Jazdi, Haonan Chen, Michael Weyrich

专题命中仿真与规划：simulation model(title,abstract)；分类 cs.AI、cs.RO、cs.MA

Comments Submitted to IEEE-ETFA2024, under peer-review

2310.18552 2023-10-31 physics.chem-ph cs.CE cs.LG 62%

The Role of Reference Points in Machine-Learned Atomistic Simulation Models

Xiangyun Lei, Weike Ye, Joseph Montoya, Tim Mueller, Linda Hung, Jens Hummelshoej

专题命中仿真与规划：environment model(abstract)；simulation model(title)；分类 cs.LG

2607.09336 2026-07-13 cs.LG cs.AI cs.RO 新提交 60%

Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning

用于高效离线强化学习的捷径轨迹规划

Guanquan Wang, Yoshimasa Tsuruoka

机构 * The University of Tokyo（东京大学）

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG、cs.RO

AI总结研究针对离线强化学习中轨迹规划器的问题，提出捷径轨迹规划（STP）框架，将捷径模型作为轨迹生成器，单阶段训练条件捷径轨迹模型，支持可调推理，用增强可行性感知校正的评论家选候选计划，在多任务基准测试中性能强且简化训练管道。

Comments 16 pages, 3 figures

2602.18694 2026-02-24 cs.LG cs.AI 60%

In-Context Planning with Latent Temporal Abstractions

基于潜在时间抽象的上下文规划

Baiting Luo, Yunuo Zhang, Nathaniel S. Keplinger, Samir Gupta, Abhishek Dubey, Ayan Mukhopadhyay

机构 * Vanderbilt University（范德比大学）； William & Mary（威廉与玛丽学院）

专题命中仿真与规划：latent dynamics(abstract)；分类 cs.AI、cs.LG；dynamics model(abstract)

AI总结 I-TAP通过学习离散时间抽象空间，实现高效且鲁棒的上下文规划，在部分可观测和随机动态环境中表现优异。

2505.15754 2025-10-23 cs.LG cs.AI cs.RO 60%

Improving planning and MBRL with temporally-extended actions

Palash Chatterjee, Roni Khardon

机构 * Indiana University（印第安纳大学）

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG、cs.RO

Comments NeurIPS 2025. For project website, see https://pecey.github.io/MBRL-with-TEA/

2502.19009 2025-02-27 cs.LG cs.AI 60%

Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning

Jaehyeon Son, Soochan Lee, Gunhee Kim

专题命中仿真与规划：model-based RL(abstract)；分类 cs.AI、cs.LG；dynamics model(abstract)

Comments ICLR 2025

2405.11778 2024-05-21 cs.LG cs.AI cs.MA 60%

Efficient Multi-agent Reinforcement Learning by Planning

Qihan Liu, Jianing Ye, Xiaoteng Ma, Jun Yang, Bin Liang, Chongjie Zhang

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG、cs.MA

Comments ICLR2024

2304.11241 2023-12-25 cs.CV cs.LG cs.RO 60%

AutoNeRF: Training Implicit Scene Representations with Autonomous Agents

Pierre Marza, Laetitia Matignon, Olivier Simonin, Dhruv Batra, Christian Wolf, Devendra Singh Chaplot

专题命中仿真与规划：environment model(abstract)；分类 cs.LG、cs.CV、cs.RO

2205.09991 2022-12-22 cs.LG cs.AI 60%

Planning with Diffusion for Flexible Behavior Synthesis

Michael Janner, Yilun Du, Joshua B. Tenenbaum, Sergey Levine

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG；dynamics model(abstract)

Comments ICML 2022 (long talk). Project page and code at https://diffusion-planning.github.io/

2206.07989 2022-10-11 cs.LG cs.AI 60%

Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination

Jiafei Lyu, Xiu Li, Zongqing Lu

专题命中仿真与规划：model-based RL(abstract)；分类 cs.AI、cs.LG；dynamics model(abstract)

Comments NeurIPS 2022

2006.15009 2022-04-01 cs.LG cs.AI cs.RO stat.ML 60%

A Unifying Framework for Reinforcement Learning and Planning

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

专题命中仿真与规划：model-based RL(abstract)；分类 cs.AI、cs.LG、cs.RO

2106.10544 2022-01-25 cs.AI cs.LG cs.RO 60%

Learning Space Partitions for Path Planning

Kevin Yang, Tianjun Zhang, Chris Cummins, Brandon Cui, Benoit Steiner, Linnan Wang, Joseph E. Gonzalez, Dan Klein, Yuandong Tian

专题命中仿真与规划：model-based RL(abstract)；分类 cs.AI、cs.LG、cs.RO

Journal ref NeurIPS 2021

2011.12690 2021-09-27 cs.LG cs.CV cs.RO cs.SY eess.SY 60%

DeepKoCo: Efficient latent planning with a task-relevant Koopman representation

Bas van der Heijden, Laura Ferranti, Jens Kober, Robert Babuska

专题命中仿真与规划：latent dynamics(abstract)；分类 cs.LG、cs.CV、cs.RO

2106.13911 2021-06-29 cs.LG cs.AI 60%

Predictive Control Using Learned State Space Models via Rolling Horizon Evolution

Alvaro Ovalle, Simon M. Lucas

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG；predictive model(abstract)

Comments Accepted at the Bridging the Gap Between AI Planning and Reinforcement Learning (PRL) Workshop at ICAPS 2021

2010.12974 2020-10-27 cs.LG cs.RO 60%

Improving the Exploration of Deep Reinforcement Learning in Continuous Domains using Planning for Policy Search

Jakob J. Hollenstein, Erwan Renaudo, Matteo Saveriano, Justus Piater

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.LG、cs.RO；simulation model(abstract)

1910.05527 2019-10-15 cs.LG cs.RO stat.ML 60%

Regularizing Model-Based Planning with Energy-Based Models

Rinu Boney, Juho Kannala, Alexander Ilin

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.LG、cs.RO；dynamics model(abstract)

Comments Conference on Robot Learning 2019

1907.04457 2019-07-11 cs.RO cs.AI cs.LG 60%

Partially Observable Planning and Learning for Systems with Non-Uniform Dynamics

Nicholas Collins, Hanna Kurniawati

专题命中仿真与规划：environment model(abstract)；分类 cs.AI、cs.LG、cs.RO

1906.08649 2019-06-21 cs.LG cs.AI cs.RO stat.ML 60%

Exploring Model-based Planning with Policy Networks

Tingwu Wang, Jimmy Ba

专题命中仿真与规划：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG、cs.RO

Comments 8 pages, 7 figures

1805.10129 2018-05-28 cs.LG cs.AI cs.CV stat.ML 60%

Dyna Planning using a Feature Based Generative Model

Ryan Faulkner, Doina Precup

专题命中仿真与规划：environment model(abstract)；分类 cs.AI、cs.LG、cs.CV

Comments 8 pages, 7 figures

Journal ref 24th Annual Proceedings of the Advances in Neural Information Processing Systems (2010) pp. 1-9

2607.18308 2026-07-22 cs.LG cs.AI 新提交 58%

Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative

灰箱仿真模型的智能校准：一种由大语言模型驱动的替代方法

David Gómez-Guillén, Mireia Diaz, Josep Lluis Arcos, Jesús Cerquides

机构 * Catalan Institute of Oncology-IDIBELL（加泰罗尼亚肿瘤研究所-IDIBELL）； Autonomous University of Barcelona（巴塞罗那自治大学）； Centro de Investigación Biomédica en Red de Epidemiología y Salud Pública（国家公共卫生与流行病学网络生物医学研究中心）； Artificial Intelligence Research Institute, IIIA-CSIC（人工智能研究所，西班牙科学研究委员会-人工智能研究所）

专题命中仿真与规划：simulation model(title,abstract)；分类 cs.AI、cs.LG

AI总结研究灰箱仿真模型校准问题，提出用大语言模型作优化器的智能校准方法，在肛门癌仿真模型上评估，结果表明该方法在减少模型评估次数上有优势，虽迭代推理时间增加，但可审计和解释，适用于仿真时间占主导的情况。

Comments Manuscript: 19 pages, 2 figures. Appendix: 11 pages, 1 figure

1. 仿真与规划 320 篇

Imagination-Augmented Agents for Deep Reinforcement Learning

Symmetric solutions for a partial differential elliptic equation that arises in stochastic production planning with production constraints

Science, Art and Geometrical Imagination

From a Point Cloud to a Simulation Model: Bayesian Segmentation and Entropy based Uncertainty Estimation for 3D Modelling

Metacontrol for Adaptive Imagination-Based Optimization

Planning with Expectation Models for Control

Deep Imitative Models for Flexible Inference, Planning, and Control

Information-Theoretic Approach to Efficient Adaptive Path Planning for Mobile Robotic Environmental Sensing

PRISM: Protocol Refinement through Intelligent Simulation Modeling

Process Knowledge Driven Change Point Detection for Automated Calibration of Discrete Event Simulation Models Using Machine Learning

LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins

The Role of Reference Points in Machine-Learned Atomistic Simulation Models

Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning

In-Context Planning with Latent Temporal Abstractions

Improving planning and MBRL with temporally-extended actions

Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning

Efficient Multi-agent Reinforcement Learning by Planning

AutoNeRF: Training Implicit Scene Representations with Autonomous Agents

Planning with Diffusion for Flexible Behavior Synthesis

Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination

A Unifying Framework for Reinforcement Learning and Planning

Learning Space Partitions for Path Planning

DeepKoCo: Efficient latent planning with a task-relevant Koopman representation

Predictive Control Using Learned State Space Models via Rolling Horizon Evolution

Improving the Exploration of Deep Reinforcement Learning in Continuous Domains using Planning for Policy Search

Regularizing Model-Based Planning with Energy-Based Models

Partially Observable Planning and Learning for Systems with Non-Uniform Dynamics

Exploring Model-based Planning with Policy Networks

Dyna Planning using a Feature Based Generative Model

Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative