世界模型 - arXivDaily 专题

2211.08701 2022-11-17 cs.RO cs.CV cs.LG 56%

Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction

Masha Itkina, Mykel J. Kochenderfer

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

Comments Conference on Robot Learning (CoRL) 2022, 15 pages, 4 figures

2204.02392 2022-04-06 cs.RO cs.AI cs.MA 56%

Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models

Jose L. Vazquez, Alexander Liniger, Wilko Schwarting, Daniela Rus, Luc Van Gool

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

Comments accepted to L4DC

2201.02874 2022-01-11 cs.LG cs.AI 56%

Assessing Policy, Loss and Planning Combinations in Reinforcement Learning using a New Modular Architecture

Tiago Gaspar Oliveira, Arlindo L. Oliveira

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

2106.07156 2021-06-15 cs.LG cs.AI 56%

Temporal Predictive Coding For Model-Based Planning In Latent Space

Tung Nguyen, Rui Shu, Tuan Pham, Hung Bui, Stefano Ermon

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

Comments International Conference on Machine Learning

2106.04615 2021-06-11 cs.LG cs.AI stat.ML 56%

Vector Quantized Models for Planning

Sherjil Ozair, Yazhe Li, Ali Razavi, Ioannis Antonoglou, Aäron van den Oord, Oriol Vinyals

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

Comments ICML 2021

2106.00988 2021-06-03 cs.RO cs.AI 56%

OctoPath: An OcTree Based Self-Supervised Learning Approach to Local Trajectory Planning for Mobile Robots

Bogdan Trasnea, Cosmin Ginerica, Mihai Zaha, Gigel Macesanu, Claudiu Pozna, Sorin Grigorescu

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

Journal ref Sensors 2021, 21(11), 3606

2011.04021 2021-03-18 cs.AI cs.LG 56%

On the role of planning in model-based deep reinforcement learning

Jessica B. Hamrick, Abram L. Friesen, Feryal Behbahani, Arthur Guez, Fabio Viola, Sims Witherspoon, Thomas Anthony, Lars Buesing, Petar Veličković, Théophane Weber

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

Comments Published at ICLR 2021

2007.02418 2021-03-09 cs.LG cs.AI stat.ML 56%

Selective Dyna-style Planning Under Limited Model Capacity

Zaheer Abbas, Samuel Sokota, Erin J. Talvitie, Martha White

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

Comments Accepted at ICML 2020

2012.15373 2021-01-01 cs.LG cs.AI cs.CV cs.RO 56%

Model-Based Visual Planning with Self-Supervised Functional Distances

Stephen Tian, Suraj Nair, Frederik Ebert, Sudeep Dasari, Benjamin Eysenbach, Chelsea Finn, Sergey Levine

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

2011.06752 2020-11-16 cs.LG cs.NE cs.RO 56%

Critic PI2: Master Continuous Planning via Policy Improvement with Path Integrals and Deep Actor-Critic Reinforcement Learning

Jiajun Fan, He Ba, Xian Guo, Jianye Hao

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

2008.06389 2020-08-17 cs.LG cs.RO stat.ML 56%

Sample-efficient Cross-Entropy Method for Real-time Planning

Cristina Pinneri, Shambhuraj Sawant, Sebastian Blaes, Jan Achterhold, Joerg Stueckler, Michal Rolinek, Georg Martius

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

1904.01191 2020-07-31 cs.LG cs.AI stat.ML 56%

Planning with Expectation Models

Yi Wan, Zaheer Abbas, Adam White, Martha White, Richard S. Sutton

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

2004.10876 2020-07-09 cs.AI cs.RO 56%

Flexible and Efficient Long-Range Planning Through Curious Exploration

Aidan Curtis, Minjian Xin, Dilip Arumugam, Kevin Feigelis, Daniel Yamins

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

2003.00370 2020-03-03 cs.LG cs.NE cs.RO stat.ML 56%

PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference

Masashi Okada, Norio Kosaka, Tadahiro Taniguchi

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

1807.02128 2020-01-29 cs.LG cs.RO stat.ML 56%

Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems

Jung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park, Han-Lim Choi

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

Comments Neural Information Processing Systems (NeurIPS) 2018

1912.13007 2020-01-01 cs.LG stat.ML 56%

World Programs for Model-Based Learning and Planning in Compositional State and Action Spaces

Marwin H. S. Segler

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

Comments Accepted at the Generative Modeling and Model-Based Reasoning for Robotics and AI workshop at ICML 2019. Presented on June 14th 2019. See https://sites.google.com/view/mbrl-icml2019

Journal ref https://sites.google.com/view/mbrl-icml2019

1806.01825 2019-04-01 cs.AI 56%

The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces

G. Zacharias Holland, Erin J. Talvitie, Michael Bowling

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

1807.04723 2018-07-13 cs.LG cs.AI cs.CL cs.NE stat.ML 56%

The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach

Iulian Vlad Serban, Chinnadhurai Sankar, Michael Pieper, Joelle Pineau, Yoshua Bengio

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

Comments 26 pages, 2 figures, 4 tables

1803.08501 2018-03-26 cs.RO cs.LG 56%

DOP: Deep Optimistic Planning with Approximate Value Function Evaluation

Francesco Riccio, Roberto Capobianco, Daniele Nardi

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

Comments to appear as an extended abstract paper in the Proc. of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2018), Stockholm, Sweden, July 10-15, 2018, IFAAMAS. arXiv admin note: text overlap with arXiv:1803.00297

1803.00297 2018-03-02 cs.RO cs.AI 56%

Q-CP: Learning Action Values for Cooperative Planning

Francesco Riccio, Roberto Capobianco, Daniele Nardi

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

1710.05268 2017-10-18 cs.RO cs.AI cs.CV cs.LG 56%

Self-Supervised Visual Planning with Temporal Skip Connections

Frederik Ebert, Chelsea Finn, Alex X. Lee, Sergey Levine

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

Comments accepted at the Conference on Robot Learning (CoRL) 2017

1402.1958 2014-02-11 cs.AI cs.LG stat.ML 56%

Better Optimism By Bayes: Adaptive Planning with Rich Models

Arthur Guez, David Silver, Peter Dayan

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

Comments 11 pages, 11 figures

1301.2343 2013-01-14 cs.AI cs.LG 56%

Planning by Prioritized Sweeping with Small Backups

Harm van Seijen, Richard S. Sutton

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

1610.01295 2016-11-07 cs.DC cs.MA cs.PF 54%

The Simulation Model Partitioning Problem: an Adaptive Solution Based on Self-Clustering (Extended Version)

Gabriele D'Angelo

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

Journal ref Simulation Modelling Practice and Theory, Elsevier, Volume 70, January 2017 pages 1-20

1610.00749 2016-10-05 physics.soc-ph cs.MA 54%

Microscopic Pedestrian Simulation Model to Evaluate "Lane-Like Segregation" of Pedestrian Crossing

Kardi Teknomo, Yasushi Takeyama, Hajime Inamura

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

Comments 4 pages, Teknomo, Kardi; Takeyama, Yasushi; Inamura, Hajime, Microscopic Pedestrian Simulation Model to Evaluate "Lane-Like Segregation" of Pedestrian Crossing, Proceedings of Infrastructure Planning Conference Vol. 24, Kouchi, Japan Nov 2001

1610.00029 2016-10-04 cs.CV 54%

Microscopic Pedestrian Flow Characteristics: Development of an Image Processing Data Collection and Simulation Model

Kardi Teknomo

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

Comments 140 pages, Teknomo, Kardi, Microscopic Pedestrian Flow Characteristics: Development of an Image Processing Data Collection and Simulation Model, Ph.D. Dissertation, Tohoku University Japan, Sendai, 2002

1609.01808 2016-09-08 cs.MA 54%

Review on Microscopic Pedestrian Simulation Model

Kardi Teknomo, Yasushi Takeyama, Hajime Inamura

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

Comments 2 pages, Teknomo, Kardi; Takeyama, Yasushi; Inamura, Hajime, Review on Microscopic Pedestrian Simulation Model, Proceedings Japan Society of Civil Engineering Conference March 2000, Morioka, Japan, March 2000

2502.11585 2026-08-18 cs.AI 53%

Calibration of Vehicular Traffic Simulation Models by Local Optimization

Davide Andrea Guastella, Alejandro Morales-Hernàndez, Bruno Cornelis, Gianluca Bontempi

机构 * Aix Marseille University（艾克斯-马赛大学）； Université Libre de Bruxelles（布鲁塞尔自由大学）； Macq Mobility（马克 mobility（注：此处为机构名保留原文，若有标准译名可调整，当前按直译））； Vrije Universiteit Brussel（布鲁塞尔自由大学）

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

Comments Published on Springer Transportation

2607.28027 2026-07-31 cs.MA cs.AI cs.CE 新提交 53%

VISA: A Structured Description Protocol for Agent-Based Simulation Models Towards Machine Reproducibility

VISA：面向智能体可复现性的智能体仿真模型结构化描述协议

Zhou He

机构 * University of Chinese Academy of Sciences（中国科学院大学）

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

AI总结该研究提出VISA结构化描述协议，通过八个表格及可执行规则、LLM技能提升智能体模型可复现性，在三类平台的ABMs上验证了其有效性，将复现障碍转化为可处理的依赖项。

2607.24259 2026-07-28 cs.AI 新提交 53%

Generative Artificial Intelligence (GenAI) to convert images of queuing networks into verifiable simulation models: an open-weight LLM workflow approach

生成式人工智能（GenAI）将排队网络图像转换为可验证的仿真模型：一种开放权重的大语言模型工作流方法

Thomas Monks, Alison Harper, Amy Heather, Navonil Mustafee

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

AI总结研究提出Sketch2DES工作流，利用开放权重LLMs将排队网络图像转换为可验证仿真模型，经多阶段处理，在多图表评估中各阶段可靠性高，相比直接代码生成提升多项性能，证明结构化工作流模型生成对LLM辅助仿真建模的可行性。

1. 仿真与规划 323 篇

Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction

Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models

Assessing Policy, Loss and Planning Combinations in Reinforcement Learning using a New Modular Architecture

Temporal Predictive Coding For Model-Based Planning In Latent Space

Vector Quantized Models for Planning

OctoPath: An OcTree Based Self-Supervised Learning Approach to Local Trajectory Planning for Mobile Robots

On the role of planning in model-based deep reinforcement learning

Selective Dyna-style Planning Under Limited Model Capacity

Model-Based Visual Planning with Self-Supervised Functional Distances

Critic PI2: Master Continuous Planning via Policy Improvement with Path Integrals and Deep Actor-Critic Reinforcement Learning

Sample-efficient Cross-Entropy Method for Real-time Planning

Planning with Expectation Models

Flexible and Efficient Long-Range Planning Through Curious Exploration

PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference

Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems

World Programs for Model-Based Learning and Planning in Compositional State and Action Spaces

The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces

The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach

DOP: Deep Optimistic Planning with Approximate Value Function Evaluation

Q-CP: Learning Action Values for Cooperative Planning

Self-Supervised Visual Planning with Temporal Skip Connections

Better Optimism By Bayes: Adaptive Planning with Rich Models

Planning by Prioritized Sweeping with Small Backups

The Simulation Model Partitioning Problem: an Adaptive Solution Based on Self-Clustering (Extended Version)

Microscopic Pedestrian Simulation Model to Evaluate "Lane-Like Segregation" of Pedestrian Crossing

Microscopic Pedestrian Flow Characteristics: Development of an Image Processing Data Collection and Simulation Model

Review on Microscopic Pedestrian Simulation Model

Calibration of Vehicular Traffic Simulation Models by Local Optimization

VISA: A Structured Description Protocol for Agent-Based Simulation Models Towards Machine Reproducibility

Generative Artificial Intelligence (GenAI) to convert images of queuing networks into verifiable simulation models: an open-weight LLM workflow approach