We consider scenarios from the real-time strategy game StarCraft as new benchmarks for
reinforcement learning algorithms. We propose micromanagement tasks, which present the …

In this article, we describe an automatic differentiation module of PyTorch — a library designed
to enable rapid research on machine learning models. It builds upon a few projects, most …

Deep learning frameworks have often focused on either usability or speed, but not both.
PyTorch is a machine learning library that shows that these two goals are in fact compatible: it …

We describe a simple scheme that allows an agent to learn about its environment in an
unsupervised manner. Our scheme pits two versions of the same agent, Alice and Bob, against …

Recent advances in machine learning have leveraged evolutionary information in multiple
sequence alignments to predict protein structure. We demonstrate direct inference of full …

Large language models have recently been shown to develop emergent capabilities with
scale, going beyond simple pattern matching to perform higher level reasoning and generate …

We release a dataset of 65646 StarCraft replays that contains 1535 million frames and 496
million player actions. We provide full game state data along with the original replays that can …

In the field of artificial intelligence, a combination of scale in data and model capacity
enabled by unsupervised learning has led to major advances in representation learning and …

We consider the problem of predicting a protein sequence from its backbone atom coordinates.
Machine learning approaches to this problem to date have been limited by the number of …

More than three billion years of evolution have produced an image of biology encoded into
the space of natural proteins. Here we show that language models trained on tokens …