Convolutional neural networks (CNNs) were inspired by early findings in the study of
biological vision. They have since become successful tools in computer vision and state-of …

The emergence of powerful artificial intelligence (AI) is defining new research directions in
neuroscience. To date, this research has focused largely on deep neural networks trained …

Performing agile navigation with four-legged robots is a challenging task because of the
highly dynamic motions, contacts with various parts of the robot, and the limited field of view …

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 …

Animals have exquisite control of their bodies, allowing them to perform a diverse range of
behaviours. How such control is implemented by the brain, however, remains unclear …

Reinforcement learning promises to solve complex sequential-decision problems
autonomously by specifying a high-level reward function only. However, reinforcement …

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 …

Intelligent agents need to select long sequences of actions to solve complex tasks. While
humans easily break down tasks into subgoals and reach them through millions of muscle …

High-quality motion capture datasets are now publicly available, and researchers have used
them to create kinematics-based controllers that can generate plausible and diverse human …

Accurate estimation of 3D human motion from monocular video requires modeling both
kinematics (body motion without physical forces) and dynamics (motion with physical …