Picture for Insoon Yang

Insoon Yang

Generalized Continuous-Time Models for Nesterov's Accelerated Gradient Methods

Add code
Sep 02, 2024
Viaarxiv icon

Approximate Thompson Sampling for Learning Linear Quadratic Regulators with $O(\sqrt{T})$ Regret

Add code
May 29, 2024
Viaarxiv icon

On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR

Add code
Dec 09, 2023
Viaarxiv icon

Risk-Aware Wasserstein Distributionally Robust Control of Vessels in Natural Waterways

Add code
Oct 21, 2023
Viaarxiv icon

Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs

Add code
Nov 05, 2021
Viaarxiv icon

Training Wasserstein GANs without gradient penalties

Add code
Oct 27, 2021
Figure 1 for Training Wasserstein GANs without gradient penalties
Figure 2 for Training Wasserstein GANs without gradient penalties
Figure 3 for Training Wasserstein GANs without gradient penalties
Figure 4 for Training Wasserstein GANs without gradient penalties
Viaarxiv icon

Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments

Add code
Sep 15, 2021
Figure 1 for Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
Figure 2 for Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
Figure 3 for Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
Figure 4 for Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
Viaarxiv icon

Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach

Add code
May 03, 2021
Figure 1 for Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach
Figure 2 for Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach
Figure 3 for Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach
Figure 4 for Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach
Viaarxiv icon

Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls

Add code
Oct 27, 2020
Figure 1 for Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls
Figure 2 for Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls
Figure 3 for Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls
Figure 4 for Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls
Viaarxiv icon

Learning-based distributionally robust motion control with Gaussian processes

Add code
Mar 05, 2020
Figure 1 for Learning-based distributionally robust motion control with Gaussian processes
Figure 2 for Learning-based distributionally robust motion control with Gaussian processes
Figure 3 for Learning-based distributionally robust motion control with Gaussian processes
Figure 4 for Learning-based distributionally robust motion control with Gaussian processes
Viaarxiv icon