Insoon Yang

Publication Activity (10 Years)

Years Active: 2013-2024
Publications (10 Years): 80

Top Topics

Reinforcement Learning

Stochastic Systems

Motion Planning

Markov Decision Processes

Top Venues

IEEE Trans. Autom. Control.

IEEE Control. Syst. Lett.

Publications

Yeoneung Kim, Gihun Kim, Insoon Yang
Approximate Thompson Sampling for Learning Linear Quadratic Regulators with O(√T) Regret. CoRR (2024)
Minhyuk Jang, Astghik Hakobyan, Insoon Yang
Wasserstein Distributionally Robust Control and State Estimation for Partially Observable Linear Systems. CoRR (2024)
Youngchae Cho, Insoon Yang
Wasserstein Distributionally Robust Regret Minimization. IEEE Control. Syst. Lett. 8 (2024)
Jaeuk Shin, Insoon Yang
Multiparametric Analysis of Multi-Task Markov Decision Processes: Structure, Invariance, and Reducibility. IEEE Control. Syst. Lett. 8 (2024)
Jaeuk Shin, Giho Kim, Howon Lee, Joonho Han, Insoon Yang
On task-relevant loss functions in meta-reinforcement learning. L4DC (2024)
Mingyu Park, Jaeuk Shin, Insoon Yang
Anderson acceleration for partially observable Markov decision processes: A maximum entropy approach. Autom. 163 (2024)
Juan Moreno Nadales, Astghik Hakobyan, David Muñoz de la Peña, Daniel Limón, Insoon Yang
Risk-Aware Wasserstein Distributionally Robust Control of Vessels in Natural Waterways. IEEE Trans. Control. Syst. Technol. 32 (4) (2024)
Jungbin Kim, Insoon Yang
Unifying Nesterov's Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions. ICML (2023)
Youngchae Cho, Insoon Yang
Data-Driven Stochastic Optimization Using Upper Confidence Bounds: Performance Guarantees and Distributional Robustness. CDC (2023)
Astghik Hakobyan, Insoon Yang
Distributionally Robust Differential Dynamic Programming with Wasserstein Distance. CoRR (2023)
Jungbin Kim, Insoon Yang
Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels. NeurIPS (2023)
Astghik Hakobyan, Insoon Yang
Distributionally Robust Risk Map for Learning-Based Motion Planning and Control: A Semidefinite Programming Approach. IEEE Trans. Robotics 39 (1) (2023)
Juan Moreno Nadales, Astghik Hakobyan, David Muñoz de la Peña, Daniel Limón, Insoon Yang
Risk-Aware Wasserstein Distributionally Robust Control of Vessels in Natural Waterways. CoRR (2023)
Kihyun Kim, Insoon Yang
Distributional Robustness in Minimax Linear Quadratic Control with Wasserstein Distance. SIAM J. Control. Optim. 61 (2) (2023)
Yeoneung Kim, Gihun Kim, Insoon Yang
On Concentration Bounds for Bayesian Identification of Linear Non-Gaussian Systems. CDC (2023)
Astghik Hakobyan, Insoon Yang
Distributionally Robust Optimization with Unscented Transform for Learning-Based Motion Control in Dynamic Environments. ICRA (2023)
Youngchae Cho, Insoon Yang
Using affine policies to reformulate two-stage Wasserstein distributionally robust linear programs to be independent of sample size. CoRR (2023)
Jeongho Kim, Insoon Yang
Maximum Entropy Optimal Control of Continuous-Time Dynamical Systems. IEEE Trans. Autom. Control. 68 (4) (2023)
Jaeuk Shin, Giho Kim, Howon Lee, Joonho Han, Insoon Yang
On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR. CoRR (2023)
Astghik Hakobyan, Insoon Yang
Distributionally Robust Differential Dynamic Programming With Wasserstein Distance. IEEE Control. Syst. Lett. 7 (2023)
Margaret P. Chapman, Riccardo Bonalli, Kevin M. Smith, Insoon Yang, Marco Pavone, Claire J. Tomlin
Risk-Sensitive Safety Analysis Using Conditional Value-at-Risk. IEEE Trans. Autom. Control. 67 (12) (2022)
Astghik Hakobyan, Insoon Yang
Wasserstein Distributionally Robust Control of Partially Observable Linear Systems: Tractable Approximation and Performance Guarantee. CoRR (2022)
Yeoneung Kim, Insoon Yang, Kwang-Sung Jun
Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs. NeurIPS (2022)
Jaeuk Shin, Astghik Hakobyan, Mingyu Park, Yeoneung Kim, Gihun Kim, Insoon Yang
Infusing Model Predictive Control Into Meta-Reinforcement Learning for Mobile Robots in Dynamic Environments. IEEE Robotics Autom. Lett. 7 (4) (2022)
Youngchae Cho, Insoon Yang
On Affine Policies for Wasserstein Distributionally Robust Unit Commitment. CDC (2022)
Astghik Hakobyan, Insoon Yang
Wasserstein Distributionally Robust Motion Control for Collision Avoidance Using Conditional Value-at-Risk. IEEE Trans. Robotics 38 (2) (2022)
Youngchae Cho, Insoon Yang
On Affine Policies for Wasserstein Distributionally Robust Unit Commitment. CoRR (2022)
Astghik Hakobyan, Insoon Yang
Wasserstein Distributionally Robust Control of Partially Observable Linear Systems: Tractable Approximation and Performance Guarantee. CDC (2022)
Jungbin Kim, Insoon Yang
Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis. ICML (2022)
Mingyu Park, Jaeuk Shin, Insoon Yang
Anderson Acceleration for Partially Observable Markov Decision Processes: A Maximum Entropy Approach. CoRR (2022)
Yeoneung Kim, Insoon Yang
On representation formulas for optimal control: A Lagrangian perspective. CoRR (2022)
Astghik Hakobyan, Insoon Yang
Wasserstein Distributionally Robust Control of Partially Observable Linear Stochastic Systems. CoRR (2022)
Jeongho Kim, Jaeuk Shin, Insoon Yang
Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls. J. Mach. Learn. Res. 22 (2021)
Margaret P. Chapman, Riccardo Bonalli, Kevin M. Smith, Insoon Yang, Marco Pavone, Claire J. Tomlin
Risk-sensitive safety analysis using Conditional Value-at-Risk. CoRR (2021)
Astghik Hakobyan, Insoon Yang
Toward Improving the Distributional Robustness of Risk-Aware Controllers in Learning-Enabled Environments. CDC (2021)
Kihyun Kim, Insoon Yang
Distributional robustness in minimax linear quadratic control with Wasserstein distance. CoRR (2021)
Jaeuk Shin, Astghik Hakobyan, Mingyu Park, Yeoneung Kim, Gihun Kim, Insoon Yang
Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments. CoRR (2021)
Melike Ermis, Mingyu Park, Insoon Yang
On Anderson Acceleration for Partially Observable Markov Decision Processes. CDC (2021)
Melike Ermis, Mingyu Park, Insoon Yang
On Anderson acceleration for partially observable Markov decision processes. CoRR (2021)
Astghik Hakobyan, Insoon Yang
Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach. CoRR (2021)
Insoon Yang
Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach. IEEE Trans. Autom. Control. 66 (8) (2021)
Yeoneung Kim, Insoon Yang, Kwang-Sung Jun
Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs. CoRR (2021)
Dohyun Kwon, Yeoneung Kim, Guido Montúfar, Insoon Yang
Training Wasserstein GANs without gradient penalties. CoRR (2021)
Insoon Yang
A Convex Optimization Approach to Dynamic Programming in Continuous State and Action Spaces. J. Optim. Theory Appl. 187 (1) (2020)
Astghik Hakobyan, Insoon Yang
Learning-based distributionally robust motion control with Gaussian processes. CoRR (2020)
Beomjun Kim, Jeongho Kim, Subin Huh, Seungil You, Insoon Yang
Multi-Objective Predictive Taxi Dispatch via Network Flow Optimization. CoRR (2020)
Kihyun Kim, Insoon Yang
Minimax control of ambiguous linear stochastic systems using the Wasserstein metric. CoRR (2020)
Jeongho Kim, Insoon Yang
Hamilton-Jacobi-Bellman Equations for Maximum Entropy Optimal Control. CoRR (2020)
Astghik Hakobyan, Insoon Yang
Wasserstein Distributionally Robust Motion Control for Collision Avoidance Using Conditional Value-at-Risk. CoRR (2020)
Beomjun Kim, Jeongho Kim, Subin Huh, Seungil You, Insoon Yang
Multi-Objective Predictive Taxi Dispatch via Network Flow Optimization. IEEE Access 8 (2020)
Jeongho Kim, Jaeuk Shin, Insoon Yang
Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls. CoRR (2020)
Astghik Hakobyan, Insoon Yang
Learning-Based Distributionally Robust Motion Control with Gaussian Processes. IROS (2020)
Subin Huh, Insoon Yang
Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach. CoRR (2020)
Jeongho Kim, Myeongju Kang, Dohyun Kim, Seung-Yeal Ha, Insoon Yang
A Stochastic Consensus Method for Nonconvex Optimization on the Stiefel Manifold. CDC (2020)
Melike Ermis, Insoon Yang
A3DQN: Adaptive Anderson Acceleration for Deep Q-Networks. SSCI (2020)
Astghik Hakobyan, Insoon Yang
Wasserstein Distributionally Robust Motion Planning and Control with Safety Constraints Using Conditional Value-at-Risk. ICRA (2020)
Tien-Cuong Bui, Joonyoung Kim, Taewoo Kang, Donghyeon Lee, Junyoung Choi, Insoon Yang, Kyomin Jung, Sang-Kyun Cha
STAR: Spatio-Temporal Prediction of Air Quality Using a Multimodal Approach. IntelliSys (2) (2020)
Jeongho Kim, Insoon Yang
Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time. L4DC (2020)
Kihyun Kim, Insoon Yang
Minimax Control of Ambiguous Linear Stochastic Systems Using the Wasserstein Metric. CDC (2020)
Sunho Jang, Insoon Yang
Stochastic Subgradient Methods for Dynamic Programming in Continuous State and Action Spaces. CDC (2019)
Junjie Qin, Insoon Yang, Ram Rajagopal
Submodularity of Storage Placement Optimization in Power Networks. IEEE Trans. Autom. Control. 64 (8) (2019)
Jeongho Kim, Insoon Yang
Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time. CoRR (2019)
Jeong Woo Kim, Hyungbo Shim, Insoon Yang
On Improving the Robustness of Reinforcement Learning-based Controllers using Disturbance Observer. CDC (2019)
Xinlin Wang, Insoon Yang, Sung-Hoon Ahn
Sample Efficient Home Power Anomaly Detection in Real Time Using Semi-Supervised Learning. IEEE Access 7 (2019)
Astghik Hakobyan, Gyeong Chan Kim, Insoon Yang
Risk-Aware Motion Planning and Control Using CVaR-Constrained Optimization. IEEE Robotics Autom. Lett. 4 (4) (2019)
Insoon Yang
Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach. CoRR (2018)
Samantha Samuelson, Insoon Yang
Safety-Aware Optimal Control of Stochastic Systems Using Conditional Value-at-Risk. ACC (2018)
Insoon Yang
A dynamic game approach to distributionally robust safety specifications for stochastic systems. Autom. 94 (2018)
Samantha Samuelson, Insoon Yang
Safety-Aware Optimal Control of Stochastic Systems Using Conditional Value-at-Risk. CoRR (2018)
Insoon Yang
A Convex Optimization Approach to Dynamic Programming in Continuous State and Action Spaces. CoRR (2018)
Samantha Samuelson, Insoon Yang
Data-driven distributionally robust control of energy storage to manage wind power fluctuations. CCTA (2017)
Insoon Yang, Duncan S. Callaway, Claire J. Tomlin
Variance-Constrained Risk Sharing in Stochastic Systems. IEEE Trans. Autom. Control. 62 (4) (2017)
Insoon Yang
A dynamic game approach to distributionally robust safety specifications for stochastic systems. CoRR (2017)
Insoon Yang
Distributionally robust stochastic control with conic confidence sets. CDC (2017)
Insoon Yang
A Convex Optimization Approach to Distributionally Robust Markov Decision Processes With Wasserstein Distance. IEEE Control. Syst. Lett. 1 (1) (2017)
Christopher W. Miller, Insoon Yang
Optimal Control of Conditional Value-at-Risk in Continuous Time. SIAM J. Control. Optim. 55 (2) (2017)
Insoon Yang, Samuel A. Burden, Ram Rajagopal, S. Shankar Sastry, Claire J. Tomlin
Approximation Algorithms for Optimization of Combinatorial Dynamical Systems. IEEE Trans. Autom. Control. 61 (9) (2016)
Insoon Yang, Sila Kiliccote, Ram Rajagopal, Claire J. Tomlin
Control of Supermarket Refrigeration Systems via Online Combinatorial Optimization. CoRR (2016)
Insoon Yang, Asuman E. Ozdaglar
Reducing electricity price volatility via stochastic storage control. ACC (2016)
Junjie Qin, Insoon Yang, Ram Rajagopal
Submodularity of energy storage placement in power networks. CDC (2016)
Christopher W. Miller, Insoon Yang
Optimal Dynamic Contracts for a Large-Scale Principal-Agent Hierarchy: A Concavity-Preserving Approach. CoRR (2015)
Christopher W. Miller, Insoon Yang
Optimal Control of Conditional Value-at-Risk in Continuous Time. CoRR (2015)
Insoon Yang, Duncan S. Callaway, Claire J. Tomlin
Indirect load control for electricity market risk management via risk-limiting dynamic contracts. ACC (2015)
Insoon Yang, Melanie Nicole Zeilinger, Claire J. Tomlin
Utility learning model predictive control for personal electric loads. CDC (2014)
Insoon Yang, Duncan S. Callaway, Claire J. Tomlin
Direct load control for electricity market risk management via risk-limiting dynamic contracts. Allerton (2014)
Insoon Yang, Duncan S. Callaway, Claire J. Tomlin
Dynamic contracts with partial observations: Application to indirect load control. ACC (2014)
Insoon Yang, Claire J. Tomlin
Reaction-diffusion systems in protein networks: Global existence and identification. Syst. Control. Lett. 74 (2014)
Insoon Yang, Sabine Becker-Weimann, Mina J. Bissell, Claire J. Tomlin
One-shot computation of reachable sets for differential games. HSCC (2013)
Insoon Yang, Claire J. Tomlin
Regularization-based identification for level set equations. CDC (2013)
Insoon Yang, Samuel Burden, S. Shankar Sastry, Claire J. Tomlin
Infinitesimal interconnection variation in nonlinear networked systems. CDC (2013)
Insoon Yang, Claire J. Tomlin
Identification of surface tension in mean curvature flow. ACC (2013)