Consider a robot tasked with tidying a desk with a meticulously construc...
Reward design in reinforcement learning (RL) is challenging since specif...
Many real-world applications of language models (LMs), such as code
auto...
Successful negotiators must learn how to balance optimizing for self-int...
The ability for robots to transfer their learned knowledge to new tasks ...
In order to collaborate safely and efficiently, robots need to anticipat...
To communicate with new partners in new contexts, humans rapidly form ne...
Our goal is to enable robots to express their incapability, and to do so...