works on
bayesian optimization 1heteroscedastic modeling 1hyperparameter tuning 1risk-aware reinforcement learning 1sample efficiency 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Efficient Heteroscedastic Bayesian Optimization for Risk-Aware AutoRL

Mingxuan Che, Tsung-Yuan Tseng, Theresa Eimer +2

The paper introduces ERAHBO, a Bayesian optimization approach that models both the mean and variance of reinforcement learning performance with respect to hyperparameters, aiming t…