With the widespread adoption of deep learning, reinforcement learning (RL) has
experienced a dramatic increase in popularity, scaling to previously intractable problems …

We present the Minigrid and Miniworld libraries which provide a suite of goal-oriented 2D
and 3D environments. The libraries were explicitly created with a minimalistic design …

We investigated whether deep reinforcement learning (deep RL) is able to synthesize
sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be …

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 propose a novel approach to multi-robot collaboration that harnesses the power of pre-
trained large language models (LLMs) for both high-level communication and low-level path …

This work identifies a common flaw of deep reinforcement learning (RL) algorithms: a
tendency to rely on early interactions and ignore useful evidence encountered later …

Artificial intelligence (AI) systems possess significant potential to drive societal progress.
However, their deployment often faces obstacles due to substantial safety concerns. Safe …

Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient
robot learning from visual observations. Yet the current approaches typically train a single …

A key theme in the past decade has been that when large neural networks and large
datasets combine they can produce remarkable results. In deep reinforcement learning (RL) …

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 …