120 citations · 370 across the 36 of their papers we have counts for
37 papers
Distributionally Robust Differential Dynamic Programming with Wasserstein Distance
Astghik Hakobyan, Insoon Yang
Differential dynamic programming (DDP) is a popular technique for solving nonlinear optimal control problems with locally quadratic approximations. However, existing DDP methods ar…
Unifying Nesterov's Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions: From Continuous-Time Dynamics to Discrete-Time Algorithms
Jungbin Kim, Insoon Yang
Although Nesterov's accelerated gradient (NAG) methods have been studied from various perspectives, it remains unclear why the most popular forms of NAG must handle convex and stro…
Using affine policies to reformulate two-stage Wasserstein distributionally robust linear programs to be independent of sample size
Youngchae Cho, Insoon Yang
Intensively studied in theory as a promising data-driven tool for decision-making under ambiguity, two-stage distributionally robust optimization (DRO) problems over Wasserstein ba…
Wasserstein Distributionally Robust Control of Partially Observable Linear Stochastic Systems
Astghik Hakobyan, Insoon Yang
Distributionally robust control (DRC) aims to effectively manage distributional ambiguity in stochastic systems. While most existing works address inaccurate distributional informa…
Anderson Acceleration for Partially Observable Markov Decision Processes: A Maximum Entropy Approach
Mingyu Park, Jaeuk Shin, Insoon Yang
Partially observable Markov decision processes (POMDPs) is a rich mathematical framework that embraces a large class of complex sequential decision-making problems under uncertaint…
On representation formulas for optimal control: A Lagrangian perspective
Yeoneung Kim, Insoon Yang
In this paper, we study representation formulas for finite-horizon optimal control problems with or without state constraints, unifying two different viewpoints: the Lagrangian and…
Wasserstein Distributionally Robust Control of Partially Observable Linear Systems: Tractable Approximation and Performance Guarantee
Astghik Hakobyan, Insoon Yang
Wasserstein distributionally robust control (WDRC) is an effective method for addressing inaccurate distribution information about disturbances in stochastic systems. It provides v…
On Affine Policies for Wasserstein Distributionally Robust Unit Commitment
Youngchae Cho, Insoon Yang
This paper proposes a unit commitment (UC) model based on data-driven Wasserstein distributionally robust optimization (WDRO) for power systems under uncertainty of renewable gener…
Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis
Jungbin Kim, Insoon Yang
We propose computationally tractable accelerated first-order methods for Riemannian optimization, extending the Nesterov accelerated gradient (NAG) method. For both geodesically co…
Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs
Yeoneung Kim, Insoon Yang, Kwang-Sung Jun
In online learning problems, exploiting low variance plays an important role in obtaining tight performance guarantees yet is challenging because variances are often not known a pr…
Training Wasserstein GANs without gradient penalties
Dohyun Kwon, Yeoneung Kim, Guido Montúfar +1
We propose a stable method to train Wasserstein generative adversarial networks. In order to enhance stability, we consider two objective functions using the -transform based on…
Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
Jaeuk Shin, Astghik Hakobyan, Mingyu Park +3
The successful operation of mobile robots requires them to adapt rapidly to environmental changes. To develop an adaptive decision-making tool for mobile robots, we propose a novel…
Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach
Astghik Hakobyan, Insoon Yang
This paper proposes a novel safety specification tool, called the distributionally robust risk map (DR-risk map), for a mobile robot operating in a learning-enabled environment. Gi…
On Anderson acceleration for partially observable Markov decision processes
Melike Ermis, Mingyu Park, Insoon Yang
This paper proposes an accelerated method for approximately solving partially observable Markov decision process (POMDP) problems offline. Our method carefully combines two existin…
Distributional robustness in minimax linear quadratic control with Wasserstein distance
Kihyun Kim, Insoon Yang
To address the issue of inaccurate distributions in practical stochastic systems, a minimax linear-quadratic control method is proposed using the Wasserstein metric. Our method aim…
Risk-sensitive safety analysis using Conditional Value-at-Risk
Margaret P. Chapman, Riccardo Bonalli, Kevin M. Smith +3
This paper develops a safety analysis method for stochastic systems that is sensitive to the possibility and severity of rare harmful outcomes. We define risk-sensitive safe sets a…
Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls
Jeongho Kim, Jaeuk Shin, Insoon Yang
In this paper, we propose Q-learning algorithms for continuous-time deterministic optimal control problems with Lipschitz continuous controls. Our method is based on a new class of…
Hamilton-Jacobi-Bellman Equations for Maximum Entropy Optimal Control
Jeongho Kim, Insoon Yang
Maximum entropy reinforcement learning (RL) methods have been successfully applied to a range of challenging sequential decision-making and control tasks. However, most of existing…
Multi-Objective Predictive Taxi Dispatch via Network Flow Optimization
Beomjun Kim, Jeongho Kim, Subin Huh +2
In this paper, we discuss a large-scale fleet management problem in a multi-objective setting. We aim to seek a receding horizon taxi dispatch solution that serves as many ride req…
Minimax control of ambiguous linear stochastic systems using the Wasserstein metric
Kihyun Kim, Insoon Yang
In this paper, we propose a minimax linear-quadratic control method to address the issue of inaccurate distribution information in practical stochastic systems. To construct a cont…
Learning-based distributionally robust motion control with Gaussian processes
Astghik Hakobyan, Insoon Yang
Safety is a critical issue in learning-based robotic and autonomous systems as learned information about their environments is often unreliable and inaccurate. In this paper, we pr…
Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach
Subin Huh, Insoon Yang
Emerging applications in robotics and autonomous systems, such as autonomous driving and robotic surgery, often involve critical safety constraints that must be satisfied even when…
Wasserstein Distributionally Robust Motion Control for Collision Avoidance Using Conditional Value-at-Risk
Astghik Hakobyan, Insoon Yang
In this paper, a risk-aware motion control scheme is considered for mobile robots to avoid randomly moving obstacles when the true probability distribution of uncertainty is unknow…
Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time
Jeongho Kim, Insoon Yang
In this paper, we introduce Hamilton-Jacobi-Bellman (HJB) equations for Q-functions in continuous time optimal control problems with Lipschitz continuous controls. The standard Q-f…