AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

This paper presents an experimental study regarding the use of OpenAI's ChatGPT for
robotics applications. We outline a strategy that combines design principles for prompt …

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …

Large language models (LLMs) have demonstrated exciting progress in acquiring diverse
new capabilities through in-context learning, ranging from logical reasoning to code-writing …

Can world knowledge learned by large language models (LLMs) be used to act in
interactive environments? In this paper, we investigate the possibility of grounding high-level …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

A long-term goal of AI research is to build intelligent agents that can communicate with
humans in natural language, perceive the environment, and perform real-world tasks. Vision …

We study the problem of learning a range of vision-based manipulation tasks from a large
offline dataset of robot interaction. In order to accomplish this, humans need easy and …

We introduce BEHAVIOR, a benchmark for embodied AI with 100 activities in simulation,
spanning a range of everyday household chores such as cleaning, maintenance, and food …

The history of learning for control has been an exciting back and forth between two broad
classes of algorithms: planning and reinforcement learning. Planning algorithms effectively …