As materials researchers increasingly embrace machine-learning (ML) methods, it is natural
to wonder what lessons can be learned from other fields undergoing similar developments …

In this tutorial article, we aim to provide the reader with the conceptual tools needed to get
started on research on offline reinforcement learning algorithms: reinforcement learning …

Developing a general algorithm that learns to solve tasks across a wide range of
applications has been a fundamental challenge in artificial intelligence. Although current …

Model-based reinforcement learning methods often use learning only for the purpose of
estimating an approximate dynamics model, offloading the rest of the decision-making work …

We present a framework for video modeling based on denoising diffusion probabilistic
models that produces long-duration video completions in a variety of realistic environments …

Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing
their relative performance on a large suite of tasks. Most published results on deep RL …

This work identifies a common flaw of deep reinforcement learning (RL) algorithms: a
tendency to rely on early interactions and ignore useful evidence encountered later …

Intelligent agents need to generalize from past experience to achieve goals in complex
environments. World models facilitate such generalization and allow learning behaviors …

Foundation models pretrained on diverse data at scale have demonstrated extraordinary
capabilities in a wide range of vision and language tasks. When such models are deployed …

We introduce a value-based RL agent, which we call BBF, that achieves super-human
performance in the Atari 100K benchmark. BBF relies on scaling the neural networks used …