The scale of Internet-connected systems has increased considerably, and these systems are
being exposed to cyberattacks more than ever. The complexity and dynamics of …

Inspired by progress in large-scale language modeling, we apply a similar approach
towards building a single generalist agent beyond the realm of text outputs. The agent …

We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual
continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data …

We propose a simple data augmentation technique that can be applied to standard model-
free reinforcement learning algorithms, enabling robust learning directly from pixels without …

We demonstrate that models trained only in simulation can be used to solve a manipulation
problem of unprecedented complexity on a real robot. This is made possible by two key …

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 …

Planning has been very successful for control tasks with known environment dynamics. To
leverage planning in unknown environments, the agent needs to learn the dynamics from …

We propose a simple data augmentation technique that can be applied to standard model-
free reinforcement learning algorithms, enabling robust learning directly from pixels without …