L4DC 2024

139 papers

Restless bandits with rewards generated by a linear Gaussian dynamical system

Jonathan Gornet, Bruno Sinopoli

Efficient imitation learning with conservative world models

Victor Kolev, Rafael Rafailov, Kyle Hatch, Jiajun Wu, Chelsea Finn

Proto-MPC: An encoder-prototype-decoder approach for quadrotor control in challenging winds

Yuliang Gu, Sheng Cheng, NAIRA HOVAKIMYAN

Physics-constrained learning of PDE systems with uncertainty quantified port-Hamiltonian models

Kaiyuan Tan, Peilun Li, Thomas Beckers

Adaptive neural network based control approach for building energy control under changing environmental conditions

Lilli Frison, Simon Gölzhäuser

Pontryagin neural operator for solving general-sum differential games with parametric state constraints

Lei Zhang, Mukesh Ghimire, Zhe Xu, Wenlong Zhang, Yi Ren

Reinforcement learning-driven parametric curve fitting for snake robot gait design

Jack Naish, Jacob Rodriguez, Jenny Zhang, Bryson Jones, Guglielmo Daddi

Probably approximately correct stability of allocations in uncertain coalitional games with private sampling

George Pantazis, Filiberto Fele, Filippo Fabiani, Sergio Grammatico, Kostas Margellos

Wasserstein distributionally robust regret-optimal control over infinite-horizon

Taylan Kargin, Joudi Hajar, Vikrant Malik, Babak Hassibi

Do no harm: A counterfactual approach to safe reinforcement learning

Sean Vaskov, Wilko Schwarting, Chris Baker

Hamiltonian GAN

Christine Allen-Blanchette

Growing Q-networks: Solving continuous control tasks with adaptive control resolution

Tim Seyde, Peter Werner, Wilko Schwarting, Markus Wulfmeier, Daniela Rus

Data-driven strategy synthesis for stochastic systems with unknown nonlinear disturbances

Ibon Gracia, Dimitris Boskos, Luca Laurenti, Morteza Lahijanian

Neural processes with event triggers for fast adaptation to changes

Paul Brunzema, Paul Kruse, Sebastian Trimpe

Generalized constraint for probabilistic safe reinforcement learning

Weiqin Chen, Santiago Paternain

Robust exploration with adversary via Langevin Monte Carlo

Hao-Lun Hsu, Miroslav Pajic

Deep Hankel matrices with random elements

Nathan Lawrence, Philip Loewen, Shuyuan Wang, Michael Forbes, Bhushan Gopaluni

A framework for evaluating human driver models using neuroimaging

Christopher Strong, Kaylene Stocking, Jingqi Li, Tianjiao Zhang, Jack Gallant

A deep learning approach for distributed aggregative optimization with users’ Feedback

Riccardo Brumali, Guido Carnevale, Giuseppe Notarstefano

QCQP-Net: Reliably learning feasible alternating current optimal power flow solutions under constraints

Sihan Zeng, Youngdae Kim, Yuxuan Ren, Kibaek Kim

DC4L: Distribution shift recovery via data-driven control for deep learning models

Vivian Lin, Kuk Jin Jang, Souradeep Dutta, Michele Caprio, Oleg Sokolsky

Data-driven simulator for mechanical circulatory support with domain adversarial neural process

Sophia Sun, Wenyuan Chen, Zihao Zhou, Sonia Fereidooni, Elise Jortberg

Can a transformer represent a Kalman filter?

Gautam Goel, Peter Bartlett

Adaptive teaching in heterogeneous agents: Balancing surprise in sparse reward scenarios

Emma Clark, Kanghyun Ryu, Negar Mehr

Data driven verification of positive invariant sets for discrete, nonlinear systems

Amy K. Strong, Leila J. Bridgeman

Multi-agent coverage control with transient behavior consideration

Runyu Zhang, Haitong Ma, Na Li

CACTO-SL: Using Sobolev learning to improve continuous actor-critic with trajectory optimization

Elisa Alboni, Gianluigi Grandesso, Gastone Pietro Rosati Papini, Justin Carpentier, Andrea Del Prete

Distributed on-the-fly control of multi-agent systems with unknown dynamics: Using limited data to obtain near-optimal control

Shayan Meshkat Alsadat, Nasim Baharisangari, Zhe Xu

STEMFold: Stochastic temporal manifold for multi-agent interactions in the presence of hidden agents

Hemant Kumawat, Biswadeep Chakraborty, Saibal Mukhopadhyay

Physically consistent modeling & identification of nonlinear friction with dissipative Gaussian processes

Rui Dai, Giulio Evangelisti, Sandra Hirche

Increasing information for model predictive control with semi-Markov decision processes

Rémy Hosseinkhan Boucher, Stella Douka, Onofrio Semeraro, Lionel Mathelin

Convex neural network synthesis for robustness in the 1-norm

Ross Drummond, Chris Guiver, Matthew Turner

How safe am I given what I see? Calibrated prediction of safety chances for image-controlled autonomy

Zhenjiang Mao, Carson Sobolewski, Ivan Ruchkin

Learning locally interacting discrete dynamical systems: Towards data-efficient and scalable prediction

Beomseok Kang, Harshit Kumar, Minah Lee, Biswadeep Chakraborty, Saibal Mukhopadhyay

Multi-modal conformal prediction regions by optimizing convex shape templates

Renukanandan Tumu, Matthew Cleaveland, Rahul Mangharam, George Pappas, Lars Lindemann

Recursively feasible shrinking-horizon MPC in dynamic environments with conformal prediction guarantees

Charis Stamouli, Lars Lindemann, George Pappas

Dynamics harmonic analysis of robotic systems: Application in data-driven Koopman modelling

Daniel Ordonez-Apraez, Vladimir Kostic, Giulio Turrisi, Pietro Novelli, Carlos Mastalli

From raw data to safety: Reducing conservatism by set expansion

Mohammad Bajelani, Klaske Van Heusden

Lagrangian inspired polynomial estimator for black-box learning and control of underactuated systems

Giulio Giacomuzzo, Riccardo Cescon, Diego Romeres, Ruggero Carli, Alberto Dalla Libera

Safety filters for black-box dynamical systems by learning discriminating hyperplanes

Will Lavanakul, Jason Choi, Koushil Sreenath, Claire Tomlin

Learning true objectives: Linear algebraic characterizations of identifiability in inverse reinforcement learning

Mohamad Louai Shehab, Antoine Aspeel, Nikos Arechiga, Andrew Best, Necmiye Ozay

Towards model-free LQR control over rate-limited channels

Aritra Mitra, Lintao Ye, Vijay Gupta

A multi-modal distributed learning algorithm in reproducing kernel Hilbert spaces

Aneesh Raghavan, Karl Henrik Johansson

Mapping back and forth between model predictive control and neural networks

Ross Drummond, Pablo Baldivieso, Giorgio Valmorbida

PlanNetX: Learning an efficient neural network planner from MPC for longitudinal control

Jasper Hoffmann, Diego Fernandez Clausen, Julien Brosseit, Julian Bernhard, Klemens Esterle

Multi-agent assignment via state augmented reinforcement learning

Leopoldo Agorio, Sean Van Alen, Miguel Calvo-Fullana, Santiago Paternain, Juan Andrés Bazerque

State-wise safe reinforcement learning with pixel observations

Sinong Zhan, Yixuan Wang, Qingyuan Wu, Ruochen Jiao, Chao Huang

On task-relevant loss functions in meta-reinforcement learning

Jaeuk Shin, Giho Kim, Howon Lee, Joonho Han, Insoon Yang

A learning-based framework to adapt legged robots on-the-fly to unexpected disturbances

Nolan Fey, He Li, Nicholas Adrian, Patrick Wensing, Michael Lemmon

Data-driven bifurcation analysis via learning of homeomorphism

Wentao Tang

Stable modular control via contraction theory for reinforcement learning

Bing Song, Jean-Jacques Slotine, Quang-Cuong Pham

CoVO-MPC: Theoretical analysis of sampling-based MPC and optimal covariance design

Zeji Yi, Chaoyi Pan, Guanqi He, Guannan Qu, Guanya Shi

Residual learning and context encoding for adaptive offline-to-online reinforcement learning

Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen

Towards bio-inspired control of aerial vehicle: Distributed aerodynamic parameters for state prediction

Yikang Wang, Adolfo Perrusquia, Dmitry Ignatyev

PDE control gym: A benchmark for data-driven boundary control of partial differential equations

Luke Bhan, Yuexin Bian, Miroslav Krstic, Yuanyuan Shi

Convex approximations for a bi-level formulation of data-enabled predictive control

Xu Shang, Yang Zheng

Convergence guarantees for adaptive model predictive control with kinky inference

Riccardo Zuliani, Raffaele Soloperto, John Lygeros

Finite-time complexity of incremental policy gradient methods for solving multi-task reinforcement learning

Yitao Bai, Thinh Doan

Event-triggered safe Bayesian optimization on quadcopters

Antonia Holzapfel, Paul Brunzema, Sebastian Trimpe

Probabilistic ODE solvers for integration error-aware numerical optimal control

Amon Lahr, Filip Tronarp, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig

Parameterized fast and safe tracking (FaSTrack) using DeepReach

Hyun Joe Jeong, Zheng Gong, Somil Bansal, Sylvia Herbert

Error bounds, PL condition, and quadratic growth for weakly convex functions, and linear convergences of proximal point methods

Feng-Yi Liao, Lijun Ding, Yang Zheng

Nonasymptotic regret analysis of adaptive linear quadratic control with model misspecification

Bruce Lee, Anders Rantzer, Nikolai Matni

System-level safety guard: Safe tracking control through uncertain neural network dynamics models

Xiao Li, Yutong Li, Anouck Girard, Ilya Kolmanovsky

Bounded robustness in reinforcement learning via lexicographic objectives

Daniel Jarne Ornia, Licio Romao, Lewis Hammond, Manuel Mazo Jr, Alessandro Abate

In vivo learning-based control of microbial populations density in bioreactors

Sara Maria Brancato, Davide Salzano, Francesco De Lellis, Davide Fiore, Giovanni Russo

Deep model-free KKL observer: A switching approach

Johan Peralez, Madiha Nadri

A large deviations perspective on policy gradient algorithms

Wouter Jongeneel, Daniel Kuhn, Mengmeng Li

Meta-learning linear quadratic regulators: a policy gradient MAML approach for model-free LQR

Leonardo Felipe Toso, Donglin Zhan, James Anderson, Han Wang

Conditions for parameter unidentifiability of linear ARX systems for enhancing security

Xiangyu Mao, Jianping He, Chengpu Yu, Chongrong Fang

Learning robust policies for uncertain parametric Markov decision processes

Luke Rickard, Alessandro Abate, Kostas Margellos

Design of observer-based finite-time control for inductively coupled power transfer system with random gain fluctuations

Satheesh Thangavel, Sakthivel Rathinasamy

Mixing classifiers to alleviate the accuracy-robustness trade-off

Yatong Bai, Brendon G. Anderson, Somayeh Sojoudi

Towards safe multi-task Bayesian optimization

Jannis Lübsen, Christian Hespe, Annika Eichler

SpOiLer: Offline reinforcement learning using scaled penalties

Padmanaba Srinivasan, William J. Knottenbelt

Improving sample efficiency of high dimensional Bayesian optimization with MCMC

Zeji Yi, Yunyue Wei, Chu Xin Cheng, Kaibo He, Yanan Sui

Uncertainty informed optimal resource allocation with Gaussian process based Bayesian inference

Samarth Gupta, Saurabh Amin

Learning ε-Nash equilibrium stationary policies in stochastic games with unknown independent chains using online mirror descent

Tiancheng Qin, S. Rasoul Etesami

Robust cooperative multi-agent reinforcement learning: A mean-field type game perspective

Muhammad Aneeq Uz Zaman, Mathieu Lauriere, Alec Koppel, Tamer Basar

Rademacher complexity of neural ODEs via Chen-Fliess series

Joshua Hanson, Maxim Raginsky

Hacking predictors means hacking cars: Using sensitivity analysis to identify trajectory prediction vulnerabilities for autonomous driving security

Marsalis Gibson, David Babazadeh, Claire Tomlin, Shankar Sastry

Random features approximation for control-affine systems

Kimia Kazemian, Yahya Sattar, Sarah Dean

Verification of neural reachable tubes via scenario optimization and conformal prediction

Albert Lin, Somil Bansal

Expert with clustering: Hierarchical online preference learning framework

Tianyue Zhou, Jung-Hoon Cho, Babak Rahimi Ardabili, Hamed Tabkhi, Cathy Wu

Pointwise-in-time diagnostics for reinforcement learning during training and runtime

Noel Brindise, Andres Posada Moreno, Cedric Langbort, Sebastian Trimpe

Combining model-based controller and ML advice via convex reparameterization

Junxuan Shen, Adam Wierman, Guannan Qu

Data-driven robust covariance control for uncertain linear systems

Joshua Pilipovsky, Panagiotis Tsiotras

On the nonsmooth geometry and neural approximation of the optimal value function of infinite-horizon pendulum swing-up

Haoyu Han, Heng Yang

An invariant information geometric method for high-dimensional online optimization

Zhengfei Zhang, Yunyue Wei, Yanan Sui

Balanced reward-inspired reinforcement learning for autonomous vehicle racing

Zhen Tian, Dezong Zhao, Zhihao Lin, David Flynn, Wenjing Zhao

Efficient skill acquisition for insertion tasks in obstructed environments

Jun Yamada, Jack Collins, Ingmar Posner

Safe learning in nonlinear model predictive control

Johannes Buerger, Mark Cannon, Martin Doff-Sotta

Learning flow functions of spiking systems

Miguel Aguiar, Amritam Das, Karl H. Johansson

Learning and deploying robust locomotion policies with minimal dynamics randomization

Luigi Campanaro, Siddhant Gangapurwala, Wolfgang Merkt, Ioannis Havoutis

Submodular information selection for hypothesis testing with misclassification penalties

Jayanth Bhargav, Mahsa Ghasemi, Shreyas Sundaram

Neural operators for boundary stabilization of stop-and-go traffic

Yihuai Zhang, Ruiguo Zhong, Huan Yu

Learning for CasADi: Data-driven Models in Numerical Optimization

Tim Salzmann, Jon Arrizabalaga, Joel Andersson, Marco Pavone, Markus Ryll

Uncertainty quantification and robustification of model-based controllers using conformal prediction

Kong Yao Chee, Thales C. Silva, M. Ani Hsieh, George J. Pappas

Nonconvex scenario optimization for data-driven reachability

Elizabeth Dietrich, Alex Devonport, Murat Arcak

A data-driven Riccati equation

Anders Rantzer