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 …

Dexterous manipulation of the robot is an important part of realizing intelligence, but
manipulators can only perform simple tasks such as sorting and packing in a structured …

Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data.
Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms …

A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization
from existing datasets followed by fast online fine-tuning with limited interaction. However …

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 …

While behavior learning has made impressive progress in recent times, it lags behind
computer vision and natural language processing due to its inability to leverage large …

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 …

robosuite is a simulation framework for robot learning powered by the MuJoCo physics
engine. It offers a modular design for creating robotic tasks as well as a suite of benchmark …

We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies that
can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The …

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 …