L4DC 2024

139 papers

Learning-based rigid tube model predictive control

Yulong Gao, Shuhao Yan, Jian Zhou, Mark Cannon, Alessandro Abate

Online decision making with history-average dependent costs

Vijeth Hebbar, Cedric Langbort

Signatures meet dynamic programming: Generalizing Bellman equations for trajectory following

Motoya Ohnishi, Iretiayo Akinola, Jie Xu, Ajay Mandlekar, Fabio Ramos

Understanding the difficulty of solving Cauchy problems with PINNs

Tao Wang, Bo Zhao, Sicun Gao, Rose Yu

Decision boundary learning for safe vision-based navigation via Hamilton-Jacobi reachability analysis and support vector machine

Tara Toufighi, Minh Bui, Rakesh Shrestha, Mo Chen

On the uniqueness of solution for the Bellman equation of LTL objectives

Zetong Xuan, Alper Bozkurt, Miroslav Pajic, Yu Wang

Real-world fluid directed rigid body control via deep reinforcement learning

Mohak Bhardwaj, Thomas Lampe, Michael Neunert, Francesco Romano, Abbas Abdolmaleki

MPC-inspired reinforcement learning for verifiable model-free control

Yiwen Lu, Zishuo Li, Yihan Zhou, Na Li, Yilin Mo

Learning soft constrained MPC value functions: Efficient MPC design and implementation providing stability and safety guarantees

Nicolas Chatzikiriakos, Kim Peter Wabersich, Felix Berkel, Patricia Pauli, Andrea Iannelli

Inverse optimal control as an errors-in-variables problem

Rahel Rickenbach, Anna Scampicchio, Melanie N. Zeilinger

Õ(T^-1) Convergence to (coarse) correlated equilibria in full-information general-sum Markov games

Weichao Mao, Haoran Qiu, Chen Wang, Hubertus Franke, Zbigniew Kalbarczyk

Parameter-adaptive approximate MPC: Tuning neural-network controllers without retraining

Henrik Hose, Alexander Gräfe, Sebastian Trimpe

Piecewise regression via mixed-integer programming for MPC

Dieter Teichrib, Moritz Schulze Darup

Adapting image-based RL policies via predicted rewards

Weiyao Wang, Xinyuan Fang, Gregory Hager

An efficient data-based off-policy Q-learning algorithm for optimal output feedback control of linear systems

Mohammad Alsalti, Victor G. Lopez, Matthias A. Müller

Minimax dual control with finite-dimensional information state

Olle Kjellqvist

Uncertainty quantification of set-membership estimation in control and perception: Revisiting the minimum enclosing ellipsoid

Yukai Tang, Jean-Bernard Lasserre, Heng Yang

Soft convex quantization: revisiting Vector Quantization with convex optimization

Tanmay Gautam, Reid Pryzant, Ziyi Yang, Chenguang Zhu, Somayeh Sojoudi

Global rewards in multi-agent deep reinforcement learning for autonomous mobility on demand systems

Heiko Hoppe, Tobias Enders, Quentin Cappart, Maximilian Schiffer

Adaptive online non-stochastic control

Naram Mhaisen, George Iosifidis

Physics-informed Neural Networks with Unknown Measurement Noise

Philipp Pilar, Niklas Wahlström

Interpretable data-driven model predictive control of building energy systems using SHAP

Patrick Henkel, Tobias Kasperski, Phillip Stoffel, Dirk Müller

Strengthened stability analysis of discrete-time Lurie systems involving ReLU neural networks

Carl Richardson, Matthew Turner, Steve Gunn, Ross Drummond

On the convergence of adaptive first order methods: Proximal gradient and alternating minimization algorithms

Puya Latafat, Andreas Themelis, Panagiotis Patrinos

Controlgym: Large-scale control environments for benchmarking reinforcement learning algorithms

Xiangyuan Zhang, Weichao Mao, Saviz Mowlavi, Mouhacine Benosman, Tamer Basar

Safe online convex optimization with multi-point feedback

Spencer Hutchinson, Mahnoosh Alizadeh

Safe dynamic pricing for nonstationary network resource allocation

Berkay Turan, Spencer Hutchinson, Mahnoosh Alizadeh

Learning “look-ahead” nonlocal traffic dynamics in a ring road

Chenguang Zhao, Huan Yu

The behavioral toolbox

Ivan Markovsky

Linearised data-driven LSTM-based control of multi-input HVAC systems

Andreas Hinderyckx, Florence Guillaume

Tracking object positions in reinforcement learning: A metric for keypoint detection

Emma Cramer, Jonas Reiher, Sebastian Trimpe

Real-time safe control of neural network dynamic models with sound approximation

Hanjiang Hu, Jianglin Lan, Changliu Liu

HSVI-based online minimax strategies for partially observable stochastic games with neural perception mechanisms

Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska

An investigation of time reversal symmetry in reinforcement learning

Brett Barkley, Amy Zhang, David Fridovich-Keil

Learning to stabilize high-dimensional unknown systems using Lyapunov-guided exploration

Songyuan Zhang, Chuchu Fan

Continual learning of multi-modal dynamics with external memory

Abdullah Akgül, Gozde Unal, Melih Kandemir

Gradient shaping for multi-constraint safe reinforcement learning

Yihang Yao, ZUXIN LIU, Zhepeng Cen, Peide Huang, Tingnan Zhang

Data-efficient, explainable and safe box manipulation: Illustrating the advantages of physical priors in model-predictive control

Achkan Salehi, Stephane Doncieux

Leveraging Hamilton-Jacobi PDEs with time-dependent Hamiltonians for continual scientific machine learning

Paula Chen, Tingwei Meng, Zongren Zou, Jérôme Darbon, George Em Karniadakis