CAGES: Cost-Aware Gradient Entropy Search for Efficient Local Multi-Fidelity Bayesian Optimization

no code implementations • 13 May 2024 • Wei-Ting Tang, Joel A. Paulson

One way to overcome this challenge is to focus on local BO methods that aim to efficiently learn gradients, which have shown strong empirical performance on a variety of high-dimensional problems including policy search in reinforcement learning (RL).

Bayesian Optimization Reinforcement Learning (RL)