With the widespread adoption of deep learning, reinforcement learning (RL) has
experienced a dramatic increase in popularity, scaling to previously intractable problems …

Machine learning (ML) systems are rapidly increasing in size, are acquiring new
capabilities, and are increasingly deployed in high-stakes settings. As with other powerful …

Abstract Design of de novo biological sequences with desired properties, like protein and
DNA sequences, often involves an active loop with several rounds of molecule ideation and …

The goal of offline black-box optimization (BBO) is to optimize an expensive black-box
function using a fixed dataset of function evaluations. Prior works consider forward …

In offline model-based optimization, we strive to maximize a black-box objective function by
only leveraging a static dataset of designs and their scores. This problem setting arises in …

Experimental design is a fundamental problem in many science and engineering fields. In
this problem, sample efficiency is crucial due to the time, money, and safety costs of real …

In this work, we decouple the iterative bi-level offline RL (value estimation and policy
extraction) from the offline training phase, forming a non-iterative bi-level paradigm and …

Offline model-based optimization aims to find a design that maximizes a property of interest
using only an offline dataset, with applications in robot, protein, and molecule design …

Using machine learning to solve combinatorial optimization (CO) problems is challenging,
especially when the data is unlabeled. This work proposes an unsupervised learning …

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