世界模型 - arXivDaily 专题

2403.10929 2024-03-19 stat.ML cs.LG 50%

Function-space Parameterization of Neural Networks for Sequential Learning

Aidan Scannell, Riccardo Mereu, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin

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

Comments 29 pages, 8 figures, Published in The Twelfth International Conference on Learning Representations

2402.09234 2024-02-16 cs.LG math.DS 50%

Multi-Hierarchical Surrogate Learning for Structural Dynamical Crash Simulations Using Graph Convolutional Neural Networks

Jonas Kneifl, Jörg Fehr, Steven L. Brunton, J. Nathan Kutz

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

2310.18112 2024-02-08 cs.RO cs.AI cs.CV cs.SY eess.SY 50%

er.autopilot 1.0: The Full Autonomous Stack for Oval Racing at High Speeds

Ayoub Raji, Danilo Caporale, Francesco Gatti, Andrea Giove, Micaela Verucchi, Davide Malatesta, Nicola Musiu, Alessandro Toschi, Silviu Roberto Popitanu, Fabio Bagni, Massimiliano Bosi, Alexander Liniger, Marko Bertogna, Daniele Morra, Francesco Amerotti, Luca Bartoli, Federico Martello, Riccardo Porta

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

Comments Preprint: Accepted to Field Robotics "Opportunities and Challenges with Autonomous Racing" Special Issue

Journal ref Field Robotics, January 2024, Volume 4

2402.04274 2024-02-08 q-bio.NC cs.LG cs.NE 50%

FPGA Deployment of LFADS for Real-time Neuroscience Experiments

Xiaohan Liu, ChiJui Chen, YanLun Huang, LingChi Yang, Elham E Khoda, Yihui Chen, Scott Hauck, Shih-Chieh Hsu, Bo-Cheng Lai

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

Comments 6 pages, 8 figures

Journal ref Fast Machine Learning for Science, ICCAD 2023

2402.02858 2024-02-06 cs.LG stat.ML 50%

Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning

Abdelhakim Benechehab, Albert Thomas, Balázs Kégl

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

2311.00168 2024-02-05 cs.LG 50%

The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback

Nathan Lambert, Roberto Calandra

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

Comments 11 pages, 5 figures

2212.14566 2024-01-17 eess.SY cs.LG cs.SY 50%

Pontryagin Optimal Control via Neural Networks

Chengyang Gu, Hui Xiong, Yize Chen

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

Comments In submission

2310.10198 2023-12-20 cs.CV cs.GR 50%

MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations

Heyuan Yao, Zhenhua Song, Yuyang Zhou, Tenglong Ao, Baoquan Chen, Libin Liu

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

Comments Project page: MoConVQ.github.io

2312.06256 2023-12-12 cs.LG cs.SY eess.SY 50%

Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems

Marco Lepri, Davide Bacciu, Cosimo Della Santina

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

Comments 11 pages, 14 Figures

2312.02682 2023-12-06 cs.LG cs.AI cs.RO 50%

H-GAP: Humanoid Control with a Generalist Planner

Zhengyao Jiang, Yingchen Xu, Nolan Wagener, Yicheng Luo, Michael Janner, Edward Grefenstette, Tim Rocktäschel, Yuandong Tian

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

Comments 18 pages including appendix, 4 figures

2311.16410 2023-11-30 math.NA cs.LG cs.NA math-ph math.MP physics.comp-ph 50%

Reduced-order modeling for parameterized PDEs via implicit neural representations

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 9 pages, 5 figures, Machine Learning and the Physical Sciences Workshop, NeurIPS 2023

2311.14910 2023-11-28 math.DS cs.LG stat.ML 50%

A latent linear model for nonlinear coupled oscillators on graphs

Agam Goyal, Zhaoxing Wu, Richard P. Yim, Binhao Chen, Zihong Xu, Hanbaek Lyu

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

Comments 23 pages, 14 figures

2310.16655 2023-10-30 cs.LG 50%

Towards Control-Centric Representations in Reinforcement Learning from Images

Chen Liu, Hongyu Zang, Xin Li, Yong Heng, Yifei Wang, Zhen Fang, Yisen Wang, Mingzhong Wang

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

2304.06040 2023-10-23 q-bio.NC cs.LG 50%

Inferring Population Dynamics in Macaque Cortex

Ganga Meghanath, Bryan Jimenez, Joseph G. Makin

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

Comments Main text: 22 pages, 6 figures, 1 table Supplementary Material: 6 pages, 8 figures, 3 tables

2310.09873 2023-10-17 cs.RO 50%

Reinforcement Learning for Reduced-order Models of Legged Robots

Yu-Ming Chen, Hien Bui, Michael Posa

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

2206.14191 2023-10-12 cs.LG cs.SY eess.SY 50%

Low Emission Building Control with Zero-Shot Reinforcement Learning

Scott R. Jeen, Alessandro Abate, Jonathan M. Cullen

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

Comments Accepted at AAAI 2023. Code available via https://enjeeneer.io/projects/pearl/

2309.07578 2023-09-15 cs.LG cs.AI cs.RO 50%

Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning

Cristina Pinneri, Sarah Bechtle, Markus Wulfmeier, Arunkumar Byravan, Jingwei Zhang, William F. Whitney, Martin Riedmiller

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

2309.05863 2023-09-13 cs.LG cs.AI cs.RO q-bio.NC 50%

The bionic neural network for external simulation of human locomotor system

Yue Shi, Shuhao Ma, Yihui Zhao

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

Comments 10

2309.05386 2023-09-12 eess.SY cs.LG cs.SY 50%

Data-Driven Model Reduction and Nonlinear Model Predictive Control of an Air Separation Unit by Applied Koopman Theory

Jan C. Schulze, Danimir T. Doncevic, Nils Erwes, Alexander Mitsos

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

Journal ref Foundations of Computer Aided Process Operations / Chemical Process Control (FOCAPO), 2023

2308.12393 2023-08-25 cs.LG cs.NA math.DS math.NA 50%

Machine learning in parameter estimation of nonlinear systems

Kaushal Kumar

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

Comments 23 pages, 7 figures,

2307.14151 2023-07-27 cs.LG stat.ML 50%

Learning Disentangled Discrete Representations

David Friede, Christian Reimers, Heiner Stuckenschmidt, Mathias Niepert

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

2211.02222 2023-07-11 cs.LG 50%

The Benefits of Model-Based Generalization in Reinforcement Learning

Kenny Young, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber

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

Comments Update to ICML version

2306.15512 2023-06-28 cs.RO 50%

Trajectory Generation, Control, and Safety with Denoising Diffusion Probabilistic Models

Nicolò Botteghi, Federico Califano, Mannes Poel, Christoph Brune

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

2210.06518 2023-06-23 cs.LG cs.AI cs.RO 50%

Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

Qinqing Zheng, Mikael Henaff, Brandon Amos, Aditya Grover

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

Comments ICML 2023. Code: https://github.com/facebookresearch/ssorl/

2306.03291 2023-06-08 cs.LG stat.ME stat.ML 50%

Switching Autoregressive Low-rank Tensor Models

Hyun Dong Lee, Andrew Warrington, Joshua I. Glaser, Scott W. Linderman

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

2305.16571 2023-05-29 cs.NI cs.AI 50%

Digital Twin-Based 3D Map Management for Edge-Assisted Mobile Augmented Reality

Conghao Zhou, Jie Gao, Mushu Li, Nan Cheng, Xuemin Shen, Weihua Zhuang

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

Comments submitted to IEEE ICCC

2211.14793 2023-05-26 eess.SY cs.GT cs.LG cs.SY 50%

A Data-driven Pricing Scheme for Optimal Routing through Artificial Currencies

David van de Sanden, Maarten Schoukens, Mauro Salazar

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

2305.09006 2023-05-17 cs.LG cs.SY eess.SY 50%

Physics-enhanced Gaussian Process Variational Autoencoder

Thomas Beckers, Qirui Wu, George J. Pappas

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

Comments Accepted paper at the 5th Annual Learning for Dynamics & Control Conference

2305.00254 2023-05-02 cs.LG stat.ML 50%

Semi-Infinitely Constrained Markov Decision Processes and Efficient Reinforcement Learning

Liangyu Zhang, Yang Peng, Wenhao Yang, Zhihua Zhang

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

Comments Shorter version accepted at NeurIPS 2022

2202.03463 2023-04-28 cs.LG cs.SY eess.SY 50%

On learning Whittle index policy for restless bandits with scalable regret

Nima Akbarzadeh, Aditya Mahajan

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

1. 模型式强化学习 1124 篇

Function-space Parameterization of Neural Networks for Sequential Learning

Multi-Hierarchical Surrogate Learning for Structural Dynamical Crash Simulations Using Graph Convolutional Neural Networks

er.autopilot 1.0: The Full Autonomous Stack for Oval Racing at High Speeds

FPGA Deployment of LFADS for Real-time Neuroscience Experiments

Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning

The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback

Pontryagin Optimal Control via Neural Networks

MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations

Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems

H-GAP: Humanoid Control with a Generalist Planner

Reduced-order modeling for parameterized PDEs via implicit neural representations

A latent linear model for nonlinear coupled oscillators on graphs

Towards Control-Centric Representations in Reinforcement Learning from Images

Inferring Population Dynamics in Macaque Cortex

Reinforcement Learning for Reduced-order Models of Legged Robots

Low Emission Building Control with Zero-Shot Reinforcement Learning

Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning

The bionic neural network for external simulation of human locomotor system

Data-Driven Model Reduction and Nonlinear Model Predictive Control of an Air Separation Unit by Applied Koopman Theory

Machine learning in parameter estimation of nonlinear systems

Learning Disentangled Discrete Representations

The Benefits of Model-Based Generalization in Reinforcement Learning

Trajectory Generation, Control, and Safety with Denoising Diffusion Probabilistic Models

Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

Switching Autoregressive Low-rank Tensor Models

Digital Twin-Based 3D Map Management for Edge-Assisted Mobile Augmented Reality

A Data-driven Pricing Scheme for Optimal Routing through Artificial Currencies

Physics-enhanced Gaussian Process Variational Autoencoder

Semi-Infinitely Constrained Markov Decision Processes and Efficient Reinforcement Learning

On learning Whittle index policy for restless bandits with scalable regret