世界模型 - arXivDaily 专题

2503.18787 2025-05-14 cs.LG math.OC 50%

Sample-Efficient Reinforcement Learning of Koopman eNMPC

Daniel Mayfrank, Mehmet Velioglu, Alexander Mitsos, Manuel Dahmen

机构 * Forschungszentrum Jülich GmbH, Institute of Climate and Energy Systems, Energy Systems Engineering (ICE-1)（茹里希研究中心有限公司，气候与能源系统研究所，能源系统工程（ICE-1））； RWTH Aachen University（亚琛工业大学）； JARA-ENERGY ； RWTH Aachen University, Process Systems Engineering (AVT.SVT)（亚琛工业大学，过程系统工程（AVT.SVT））

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

Comments 25 pages, 9 figures, 2 tables

2410.05454 2025-04-09 stat.ML cs.LG q-bio.NC 50%

Meta-Dynamical State Space Models for Integrative Neural Data Analysis

Ayesha Vermani, Josue Nassar, Hyungju Jeon, Matthew Dowling, Il Memming Park

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

2504.01766 2025-04-03 eess.SY cs.LG cs.SY 50%

Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error

Anne Somalwar, Bruce D. Lee, George J. Pappas, Nikolai Matni

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

2503.19316 2025-03-31 cs.SI 50%

A Social Dynamical System for Twitter Analysis

Zhiping Xiao, Xinyu Wang, Yifang Qin, Zijie Huang, Mason A. Porter, Yizhou Sun

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

Comments will be submitted to a journal soon

2503.12214 2025-03-18 cs.LG math.DS 50%

Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignment

Sharmita Dey, Sarath Ravindran Nair

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

2410.05602 2025-03-03 stat.ML cs.LG 50%

Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series

Byoungwoo Park, Hyungi Lee, Juho Lee

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

2406.02717 2025-03-03 quant-ph cs.LG 50%

Reinforcement learning-based architecture search for quantum machine learning

Frederic Rapp, David A. Kreplin, Marco F. Huber, Marco Roth

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

Comments 14 pages, 5 figures, 1 table; Updated authorship, and improved RL section

2406.16749 2025-02-27 cs.LG q-bio.NC stat.ML 50%

Inferring stochastic low-rank recurrent neural networks from neural data

Matthijs Pals, A Erdem Sağtekin, Felix Pei, Manuel Gloeckler, Jakob H Macke

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

Journal ref The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS) 2024

2502.18298 2025-02-26 cs.MA cs.AI cs.SY eess.SY stat.AP 50%

Smart and Efficient IoT-Based Irrigation System Design: Utilizing a Hybrid Agent-Based and System Dynamics Approach

Taha Ahmadi Pargo, Mohsen Akbarpour Shirazi, Dawud Fadai

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

Comments 50 pages, 22 figures

2502.05155 2025-02-10 cs.LG stat.ML 50%

Deep Dynamic Probabilistic Canonical Correlation Analysis

Shiqin Tang, Shujian Yu, Yining Dong, S. Joe Qin

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

Comments accepted by ICASSP-25, code is available at \url{https://github.com/marcusstang/D2PCCA}

2501.18299 2025-01-31 cs.AI 50%

Model-Free RL Agents Demonstrate System 1-Like Intentionality

Hal Ashton, Matija Franklin

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

2408.03330 2025-01-14 q-bio.NC cs.LG stat.ML 50%

Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems

Amber Hu, David Zoltowski, Aditya Nair, David Anderson, Lea Duncker, Scott Linderman

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

Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

2412.05233 2024-12-09 math.NA cs.LG cs.NA 50%

Physics-informed reduced order model with conditional neural fields

Minji Kim, Tianshu Wen, Kookjin Lee, Youngsoo Choi

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

Comments 7 pages, 2 figures, NeurIPS 2024 Workshop on Machine Learning and the Physical Sciences

2411.16019 2024-11-26 cs.LG 50%

M3: Mamba-assisted Multi-Circuit Optimization via MBRL with Effective Scheduling

Youngmin Oh, Jinje Park, Seunggeun Kim, Taejin Paik, David Pan, Bosun Hwang

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

2411.08326 2024-11-14 cs.LG cs.NA math.NA 50%

Neural Conjugate Flows: Physics-informed architectures with flow structure

Arthur Bizzi, Lucas Nissenbaum, João M. Pereira

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

2411.07971 2024-11-13 eess.SY cs.LG cs.SY 50%

Optimal Control of Mechanical Ventilators with Learned Respiratory Dynamics

Isaac Ronald Ward, Dylan M. Asmar, Mansur Arief, Jana Krystofova Mike, Mykel J. Kochenderfer

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

Comments 2024 IEEE 37th International Symposium on Computer-Based Medical Systems (CBMS), 7 pages, 3 figures

2405.19785 2024-11-12 cs.LG stat.ML 50%

Recurrent Deep Kernel Learning of Dynamical Systems

Nicolò Botteghi, Paolo Motta, Andrea Manzoni, Paolo Zunino, Mengwu Guo

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

2411.04098 2024-11-07 cs.LG cs.CE math.OC 50%

Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems

Florian Wolf, Nicolò Botteghi, Urban Fasel, Andrea Manzoni

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

2406.13633 2024-10-15 cs.LG math.OC 50%

Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation

Jaehyun Park, Junyeop Kwon, Dabeen Lee

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

2410.04553 2024-10-08 cs.LG cs.SY eess.SY 50%

Bisimulation metric for Model Predictive Control

Yutaka Shimizu, Masayoshi Tomizuka

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

2406.08805 2024-09-23 cs.LG cs.AI cs.RO 50%

A Dual Approach to Imitation Learning from Observations with Offline Datasets

Harshit Sikchi, Caleb Chuck, Amy Zhang, Scott Niekum

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

Comments 8th Conference on Robot Learning (CoRL 2024), Munich, Germany. 23 pages

2409.10045 2024-09-17 cs.LG eess.SP 50%

Learning Latent Wireless Dynamics from Channel State Information

Charbel Bou Chaaya, Abanoub M. Girgis, Mehdi Bennis

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

2404.09030 2024-08-14 eess.SY cs.LG cs.SY 50%

Active Learning for Control-Oriented Identification of Nonlinear Systems

Bruce D. Lee, Ingvar Ziemann, George J. Pappas, Nikolai Matni

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

2407.16779 2024-07-25 eess.SY cs.SY 50%

Learning Networked Dynamical System Models with Weak Form and Graph Neural Networks

Yin Yu, Daning Huang, Seho Park, Herschel C. Pangborn

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

2407.13760 2024-07-19 eess.SY cs.AI cs.SY 50%

Neural Network Tire Force Modeling for Automated Drifting

Nicholas Drake Broadbent, Trey Weber, Daiki Mori, J. Christian Gerdes

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

Comments 16th International Symposium on Advanced Vehicle Control (AVEC). September 2nd-6th, 2024. Milan, Italy

2403.13040 2024-06-28 eess.IV cs.AI cs.CV cs.LG 50%

Physics-Guided Neural Networks for Intraventricular Vector Flow Mapping

Hang Jung Ling, Salomé Bru, Julia Puig, Florian Vixège, Simon Mendez, Franck Nicoud, Pierre-Yves Courand, Olivier Bernard, Damien Garcia

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

Comments 12 pages, accepted for publication in IEEE TUFFC; camera ready corrections, corrected acknowledgments

2212.07892 2024-06-10 cs.LG math.DS nlin.CD 50%

Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics

Manuel Brenner, Florian Hess, Georgia Koppe, Daniel Durstewitz

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

Comments ICML 2024. Previously published as a workshop paper for the AAAI 2023 Workshop MLmDS as "Multimodal Teacher Forcing for Reconstructing Nonlinear Dynamical Systems"

2403.03314 2024-04-29 eess.SY cs.LG cs.MA cs.RO cs.SY 50%

Collision Avoidance Verification of Multiagent Systems with Learned Policies

Zihao Dong, Shayegan Omidshafiei, Michael Everett

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

Comments 6 pages, 6 figures

2404.04682 2024-04-09 cs.LG cs.AI cs.RO 50%

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning

Yeda Song, Dongwook Lee, Gunhee Kim

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

Comments ICLR 2024

2309.03842 2024-04-08 stat.ML cs.LG 50%

Early warning indicators via latent stochastic dynamical systems

Lingyu Feng, Ting Gao, Wang Xiao, Jinqiao Duan

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

1. 模型式强化学习 1126 篇

Sample-Efficient Reinforcement Learning of Koopman eNMPC

Meta-Dynamical State Space Models for Integrative Neural Data Analysis

Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error

A Social Dynamical System for Twitter Analysis

Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignment

Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series

Reinforcement learning-based architecture search for quantum machine learning

Inferring stochastic low-rank recurrent neural networks from neural data

Smart and Efficient IoT-Based Irrigation System Design: Utilizing a Hybrid Agent-Based and System Dynamics Approach

Deep Dynamic Probabilistic Canonical Correlation Analysis

Model-Free RL Agents Demonstrate System 1-Like Intentionality

Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems

Physics-informed reduced order model with conditional neural fields

M3: Mamba-assisted Multi-Circuit Optimization via MBRL with Effective Scheduling

Neural Conjugate Flows: Physics-informed architectures with flow structure

Optimal Control of Mechanical Ventilators with Learned Respiratory Dynamics

Recurrent Deep Kernel Learning of Dynamical Systems

Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems

Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation

Bisimulation metric for Model Predictive Control

A Dual Approach to Imitation Learning from Observations with Offline Datasets

Learning Latent Wireless Dynamics from Channel State Information

Active Learning for Control-Oriented Identification of Nonlinear Systems

Learning Networked Dynamical System Models with Weak Form and Graph Neural Networks

Neural Network Tire Force Modeling for Automated Drifting

Physics-Guided Neural Networks for Intraventricular Vector Flow Mapping

Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics

Collision Avoidance Verification of Multiagent Systems with Learned Policies

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning

Early warning indicators via latent stochastic dynamical systems