Generative protein language models are a natural way to design new proteins with desired functions.

We study offline model-based optimization to maximize a black-box objective function with a static dataset of designs and scores.

In this work, we provide a general framework for studying these problems, which we refer to as Responsible AI (RAI) games .

Uncertainty quantification (UQ) is important for reliability assessment and enhancement of machine learning models.

Recent developments in reinforcement learning (RL) led to algorithms that surpass human experts in a broad range of tasks [Mnih et al., 2015, Vinyals et al., 2019, Schrittwieser et al., 2020, Wurman et al.,