Picture for Hao-Lun Hsu

Hao-Lun Hsu

Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning

Apr 16, 2024
Viaarxiv icon

ε-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment

Mar 11, 2024
Figure 1 for ε-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment
Figure 2 for ε-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment
Figure 3 for ε-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment
Figure 4 for ε-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment
Viaarxiv icon

Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs

Add code
Dec 24, 2023
Viaarxiv icon

Robust Reinforcement Learning through Efficient Adversarial Herding

Jun 12, 2023
Figure 1 for Robust Reinforcement Learning through Efficient Adversarial Herding
Figure 2 for Robust Reinforcement Learning through Efficient Adversarial Herding
Figure 3 for Robust Reinforcement Learning through Efficient Adversarial Herding
Figure 4 for Robust Reinforcement Learning through Efficient Adversarial Herding
Viaarxiv icon

Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning

Sep 29, 2021
Figure 1 for Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning
Figure 2 for Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning
Figure 3 for Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning
Figure 4 for Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning
Viaarxiv icon