Recent advances in deep reinforcement learning (RL) have demonstrated its potential to
learn complex robotic manipulation tasks. However, RL still requires the robot to collect a …

Understanding the physical interactions of objects with environments is critical for multi-
object robotic manipulation tasks. A predictive dynamics model can predict the future states …

Robotic agents that operate autonomously in the real world need to continuously explore
their environment and learn from the data collected, with minimal human supervision. While …

Reinforcement learning (RL), imitation learning (IL), and task and motion planning (TAMP)
have demonstrated impressive performance across various robotic manipulation tasks …

Imitation Learning has empowered recent advances in learning robotic manipulation tasks
by addressing shortcomings of Reinforcement Learning such as exploration and reward …

Learning from diverse offline datasets is a promising path towards learning general purpose
robotic agents. However, a core challenge in this paradigm lies in collecting large amounts …

Benchmarks offer a scientific way to compare algorithms using objective performance
metrics. Good benchmarks have two features:(a) they should be widely useful for many …

We present Orbit, a unified and modular framework for robot learning powered by Nvidia
Isaac Sim. It offers a modular design to easily and efficiently create robotic environments …

We describe a system for deep reinforcement learning of robotic manipulation skills applied
to a large-scale real-world task: sorting recyclables and trash in office buildings. Real-world …

Experimentation on real robots is demanding in terms of time and costs. For this reason, a
large part of the reinforcement learning (RL) community uses simulators to develop and …