L4DC 2020

99 papers

Uncertain multi-agent MILPs: A data-driven decentralized solution with probabilistic feasibility guarantees

Alessandro Falsone, Federico Molinari, Maria Prandini

Improving Input-Output Linearizing Controllers for Bipedal Robots via Reinforcement Learning

Fernando Castaneda, Mathias Wulfman, Ayush Agrawal, Tyler Westenbroek, Shankar Sastry

Safe non-smooth black-box optimization with application to policy search

Ilnura Usmanova, Andreas Krause, Maryam Kamgarpour

Keyframing the Future: Keyframe Discovery for Visual Prediction and Planning

Karl Pertsch, Oleh Rybkin, Jingyun Yang, Shenghao Zhou, Konstantinos Derpanis

Improving Robustness via Risk Averse Distributional Reinforcement Learning

Rahul Singh, Qinsheng Zhang, Yongxin Chen

Policy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump Systems

Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud

Plan2Vec: Unsupervised Representation Learning by Latent Plans

Ge Yang, Amy Zhang, Ari Morcos, Joelle Pineau, Pieter Abbeel

Efficient Large-Scale Gaussian Process Bandits by Believing only Informative Actions

Amrit Singh Bedi, Dheeraj Peddireddy, Vaneet Aggarwal, Alec Koppel

A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control

Jia-Jie Zhu, Bernhard Schoelkopf, Moritz Diehl

Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation

Hany Abdulsamad, Jan Peters

Dual Stochastic MPC for Systems with Parametric and Structural Uncertainty

Elena Arcari, Lukas Hewing, Max Schlichting, Melanie Zeilinger

Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees

Jacob H. Seidman, Mahyar Fazlyab, Victor M. Preciado, George J. Pappas

A Duality Approach for Regret Minimization in Average-Award Ergodic Markov Decision Processes

Hao Gong, Mengdi Wang

Learning nonlinear dynamical systems from a single trajectory

Dylan Foster, Tuhin Sarkar, Alexander Rakhlin

Information Theoretic Model Predictive Q-Learning

Mohak Bhardwaj, Ankur Handa, Dieter Fox, Byron Boots

Data-Driven Distributed Predictive Control via Network Optimization

Ahmed Allibhoy, Jorge Cortes

L1-GP: L1 Adaptive Control with Bayesian Learning

Aditya Gahlawat, Pan Zhao, Andrew Patterson, NAIRA HOVAKIMYAN, Evangelos Theodorou

Learning to Plan via Deep Optimistic Value Exploration

Tim Seyde, Wilko Schwarting, Sertac Karaman, Daniela Rus

Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach

Yingying Li, Yujie Tang, Runyu Zhang, Na Li

Encoding Physical Constraints in Differentiable Newton-Euler Algorithm

Giovanni Sutanto, Austin Wang, Yixin Lin, Mustafa Mukadam, Gaurav Sukhatme

Lyceum: An efficient and scalable ecosystem for robot learning

Colin Summers, Kendall Lowrey, Aravind Rajeswaran, Siddhartha Srinivasa, Emanuel Todorov

Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics

Mohammad Javad Khojasteh, Vikas Dhiman, Massimo Franceschetti, Nikolay Atanasov

Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive Hands

Avishai Sintov, Andrew Kimmel, Bowen Wen, Abdeslam Boularias, Kostas Bekris

Objective Mismatch in Model-based Reinforcement Learning

Nathan Lambert, Brandon Amos, Omry Yadan, Roberto Calandra

Identifying Mechanical Models of Unknown Objects with Differentiable Physics Simulations

Changkyu Song, Abdeslam Boularias

Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time

Jeongho Kim, Insoon Yang

Feynman-Kac Neural Network Architectures for Stochastic Control Using Second-Order FBSDE Theory

Marcus Pereira, Ziyi Wang, Tianrong Chen, Emily Reed, Evangelos Theodorou

Learning Dynamical Systems with Side Information

Amir Ali Ahmadi, Bachir El Khadir

Learning for Safety-Critical Control with Control Barrier Functions

Andrew Taylor, Andrew Singletary, Yisong Yue, Aaron Ames

Toward fusion plasma scenario planning for NSTX-U using machine-learning-accelerated models

Mark Boyer

NeuralExplorer: State Space Exploration of Closed Loop Control Systems Using Neural Networks

Manish Goyal, Parasara Sridhar Duggirala

Localized Learning of Robust Controllers for Networked Systems with Dynamic Topology

Soojean Han

Model-Based Reinforcement Learning with Value-Targeted Regression

Zeyu Jia, Lin Yang, Csaba Szepesvári, Mengdi Wang

A First Principles Approach for Data-Efficient System Identification of Spring-Rod Systems via Differentiable Physics Engines

Kun Wang, Mridul Aanjaneya, Kostas Bekris

Planning from Images with Deep Latent Gaussian Process Dynamics

Nathanael Bosch, Jan Achterhold, Laura Leal-Taixé, Jorg Stuckler

Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems

Muhammad Asif Rana, Anqi Li, Dieter Fox, Byron Boots, Fabio Ramos

Constrained Upper Confidence Reinforcement Learning

Liyuan Zheng, Lillian Ratliff

Robust Regression for Safe Exploration in Control

Anqi Liu, Guanya Shi, Soon-Jo Chung, Anima Anandkumar, Yisong Yue

Robust Learning-Based Control via Bootstrapped Multiplicative Noise

Benjamin Gravell, Tyler Summers

Periodic Q-Learning

Donghwan Lee, Niao He

Stable Reinforcement Learning with Unbounded State Space

Devavrat Shah, Qiaomin Xie, Zhi Xu

Learning-based Stochastic Model Predictive Control with State-Dependent Uncertainty

Angelo Domenico Bonzanini, Ali Mesbah

Bayesian Learning with Adaptive Load Allocation Strategies

Manxi Wu, Saurabh Amin, Asuman Ozdaglar

Optimistic robust linear quadratic dual control

Jack Umenberger, Thomas B. Schön

Lambda-Policy Iteration with Randomization for Contractive Models with Infinite Policies: Well-Posedness and Convergence

Yuchao Li, Karl Henrik Johansson, Jonas Mårtensson

Learning the model-free linear quadratic regulator via random search

Hesameddin Mohammadi, Mihailo R. Jovanovic’, Mahdi Soltanolkotabi

Data-driven distributionally robust LQR with multiplicative noise

Peter Coppens, Mathijs Schuurmans, Panagiotis Patrinos

Learning supported Model Predictive Control for Tracking of Periodic References

Janine Matschek, Rolf Findeisen

Generating Robust Supervision for Learning-Based Visual Navigation Using Hamilton-Jacobi Reachability

Anjian Li, Somil Bansal, Georgios Giovanis, Varun Tolani, Claire Tomlin

Localized active learning of Gaussian process state space models

Alexandre Capone, Gerrit Noske, Jonas Umlauft, Thomas Beckers, Armin Lederer

A Theoretical Analysis of Deep Q-Learning

Jianqing Fan, Zhaoran Wang, Yuchen Xie, Zhuoran Yang

Riccati updates for online linear quadratic control

Mohammad Akbari, Bahman Gharesifard, Tamás Linder

Parameter Optimization for Learning-based Control of Control-Affine Systems

Armin Lederer, Alexandre Capone, Sandra Hirche

Bayesian model predictive control: Efficient model exploration and regret bounds using posterior sampling

Kim Peter Wabersich, Melanie Zeilinger

NeurOpt: Neural network based optimization for building energy management and climate control

Achin Jain, Francesco Smarra, Enrico Reticcioli, Alessandro D’Innocenzo, Manfred Morari

Sample Complexity of Kalman Filtering for Unknown Systems

Anastasios Tsiamis, Nikolai Matni, George Pappas

On Simulation and Trajectory Prediction with Gaussian Process Dynamics

Lukas Hewing, Elena Arcari, Lukas P. Fröhlich, Melanie N. Zeilinger

Faster saddle-point optimization for solving large-scale Markov decision processes

Joan Bas Serrano, Gergely Neu

On the Robustness of Data-Driven Controllers for Linear Systems

Rajasekhar Anguluri, Abed AlRahman Al Makdah, Vaibhav Katewa, Fabio Pasqualetti

Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability

Max Revay, Ian Manchester

Universal Simulation of Stable Dynamical Systems by Recurrent Neural Nets

Joshua Hanson, Maxim Raginsky

Fitting a Linear Control Policy to Demonstrations with a Kalman Constraint

Malayandi Palan, Shane Barratt, Alex McCauley, Dorsa Sadigh, Vikas Sindhwani

Learning Convex Optimization Control Policies

Akshay Agrawal, Shane Barratt, Stephen Boyd, Bartolomeo Stellato

Robust Guarantees for Perception-Based Control

Sarah Dean, Nikolai Matni, Benjamin Recht, Vickie Ye

Constraint Management for Batch Processes Using Iterative Learning Control and Reference Governors

Aidan Laracy, Hamid Ossareh

Data-driven Identification of Approximate Passive Linear Models for Nonlinear Systems

S. Sivaranjani, Etika Agarwal, Vijay Gupta

Structured Mechanical Models for Robot Learning and Control

Jayesh K. Gupta, Kunal Menda, Zachary Manchester, Mykel Kochenderfer

A Spatially and Temporally Attentive Joint Trajectory Prediction Framework for Modeling Vessel Intent

Jasmine Sekhon, Cody Fleming

Tractable Reinforcement Learning of Signal Temporal Logic Objectives

Harish Venkataraman, Derya Aksaray, Peter Seiler

VarNet: Variational Neural Networks for the Solution of Partial Differential Equations

Reza Khodayi-Mehr, Michael Zavlanos

Learning the Globally Optimal Distributed LQ Regulator

Luca Furieri, Yang Zheng, Maryam Kamgarpour

Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization

Homanga Bharadhwaj, Kevin Xie, Florian Shkurti

Black-box continuous-time transfer function estimation with stability guarantees: a kernel-based approach

Mirko Mazzoleni, Matteo Scandella, Simone Formentin, Fabio Previdi

Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems

Guannan Qu, Adam Wierman, Na Li

Learning Navigation Costs from Demonstrations with Semantic Observations

Tianyu Wang, Vikas Dhiman, Nikolay Atanasov

Counterfactual Programming for Optimal Control

Luiz F. O. Chamon, Santiago Paternain, Alejandro Ribeiro

Learning Constrained Dynamics with Gauss’ Principle adhering Gaussian Processes

Andreas Geist, Sebastian Trimpe

Practical Reinforcement Learning For MPC: Learning from sparse objectives in under an hour on a real robot

Napat Karnchanachari, Miguel Iglesia Valls, David Hoeller, Marco Hutter

Online Data Poisoning Attacks

Xuezhou Zhang, Xiaojin Zhu, Laurent Lessard

A Finite-Sample Deviation Bound for Stable Autoregressive Processes

Rodrigo A. González, Cristian R. Rojas

Policy Optimization for H_2 Linear Control with H_∞ Robustness Guarantee: Implicit Regularization and Global Convergence

Kaiqing Zhang, Bin Hu, Tamer Basar

Linear Antisymmetric Recurrent Neural Networks

Signe Moe, Filippo Remonato, Esten Ingar Grøtli, Jan Tommy Gravdahl

Smart Forgetting for Safe Online Learning with Gaussian Processes

Jonas Umlauft, Thomas Beckers, Alexandre Capone, Armin Lederer, Sandra Hirche

Regret Bound for Safe Gaussian Process Bandit Optimization

Sanae Amani, Mahnoosh Alizadeh, CHRISTOS THRAMPOULIDIS

Structured Variational Inference in Partially Observable Unstable Gaussian Process State Space Models

Sebastian Curi, Silvan Melchior, Felix Berkenkamp, Andreas Krause

Exploiting Model Sparsity in Adaptive MPC: A Compressed Sensing Viewpoint

Monimoy Bujarbaruah, Charlott Vallon

Feed-forward Neural Networks with Trainable Delay

Xunbi A. Ji, Tamás G. Molnár, Sergei S. Avedisov, Gábor Orosz

Learning solutions to hybrid control problems using Benders cuts

Sandeep Menta, Joseph Warrington, John Lygeros, Manfred Morari

Learning to Correspond Dynamical Systems

Nam Hee Kim, Zhaoming Xie, Michiel Panne

Bayesian joint state and parameter tracking in autoregressive models

Ismail Senoz, Albert Podusenko, Wouter M. Kouw, Bert Vries

LSTM Neural Networks: Input to State Stability and Probabilistic Safety Verification

Fabio Bonassi, Enrico Terzi, Marcello Farina, Riccardo Scattolini

Estimating Reachable Sets with Scenario Optimization

Alex Devonport, Murat Arcak

Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch Strategy

Abulikemu Abuduweili, Changliu Liu

Sparse and Low-bias Estimation of High Dimensional Vector Autoregressive Models

Trevor Ruiz, Sharmodeep Bhattacharyya, Mahesh Balasubramanian, Kristofer Bouchard

Direct Data-Driven Control with Embedded Anti-Windup Compensation

Valentina Breschi, Simone Formentin

Virtual Reference Feedback Tuning with data-driven reference model selection

Valentina Breschi, Simone Formentin

Finite-Time Performance of Distributed Two-Time-Scale Stochastic Approximation

Thinh Doan, Justin Romberg

Finite Sample System Identification: Optimal Rates and the Role of Regularization

Yue Sun, Samet Oymak, Maryam Fazel

Actively Learning Gaussian Process Dynamics

Mona Buisson-Fenet, Friedrich Solowjow, Sebastian Trimpe