Generative Adversarial Bayesian Optimization for Surrogate Objectives
CoRR(2024)
摘要
Offline model-based policy optimization seeks to optimize a learned surrogate
objective function without querying the true oracle objective during
optimization. However, inaccurate surrogate model predictions are frequently
encountered along the optimization trajectory. To address this limitation, we
propose generative adversarial Bayesian optimization (GABO) using adaptive
source critic regularization, a task-agnostic framework for Bayesian
optimization that employs a Lipschitz-bounded source critic model to constrain
the optimization trajectory to regions where the surrogate function is
reliable. We show that under certain assumptions for the continuous input space
prior, our algorithm dynamically adjusts the strength of the source critic
regularization. GABO outperforms existing baselines on a number of different
offline optimization tasks across a variety of scientific domains. Our code is
available at https://github.com/michael-s-yao/gabo
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要