Neuroscience has long been an essential driver of progress in artificial intelligence (AI). We
propose that to accelerate progress in AI, we must invest in fundamental research in …

Over the past years, numerous methods have emerged to automate the quantification of
animal behavior at a resolution not previously imaginable. This has opened up a new field of …

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy
optimization from large pre-recorded datasets without online environment interaction. It …

A key factor in the success of deep neural networks is the ability to scale models to improve
performance by varying the architecture depth and width. This simple property of neural …

The dm_control software package is a collection of Python libraries and task suites for
reinforcement learning agents in an articulated-body simulation. Infrastructure includes a …

Whether current or near-term AI systems could be conscious is a topic of scientific interest
and increasing public concern. This report argues for, and exemplifies, a rigorous and …

Offline methods for reinforcement learning have a potential to help bridge the gap between
reinforcement learning research and real-world applications. They make it possible to learn …

The cortical population code is pervaded by activity patterns evoked by movement, but it
remains largely unknown how such signals relate to natural behavior or how they might …

What are the spatial and temporal scales of brainwide neuronal activity? We used swept,
confocally-aligned planar excitation (SCAPE) microscopy to image all cells in a large …

In mammalian animal models, high-resolution kinematic tracking is restricted to brief
sessions in constrained environments, limiting our ability to probe naturalistic behaviors and …