Advanced Bandit Algorithms Research

Fixing the Measurement Model Before the Selection Heuristics: Optimiser Repairs for Living-Cell Self-Driving Laboratories

This paper compares measurement-aware models and selection-level repairs in Bayesian optimisation for living-cell experiments, finding that measurement-aware models reduce regret and improve coverage under data contamination.

Using Dynamic Bayesian Optimization to Induce Desired Effects in the Presence of Motor Learning: a Simulation Study

This study simulates human-in-the-loop optimization using Bayesian Optimization (BO) and Dynamic Bayesian Optimization (DBO) to assess DBO's effectiveness in scenarios involving motor learning, finding that DBO generally outperforms BO after sufficient iterations.

Human belief state-based exploration and exploitation in an information-selective symmetric reversal bandit task

The paper presents a task and models human decision-making in an information-selective symmetric reversal bandit task, finding participants use a belief state-based hybrid strategy.

Estimating Attentional Set-Shifting Dynamics in Varying Contextual Bandits

The paper estimates attentional set-shifting dynamics using a Non-Homogeneous Hidden Markov Model framework and compares it to classical HMMs on synthetic data.