Researchers in human–robot collaboration have extensively studied methods for inferring
human intentions and predicting their actions, as this is an important precursor for robots to …

In human-robot collaboration, both human and robotic agents must work together to achieve
a set of shared objectives. However, each team member may have individual preferences …

Artificial Intelligence is being employed by humans to collaboratively solve complicated
tasks for search and rescue, manufacturing, etc. Efficient teamwork can be achieved by …

Training agents that can coordinate zero-shot with humans is a key mission in multi-agent
reinforcement learning (MARL). Current algorithms focus on training simulated human …

As service robots become more general-purpose, they will need to adapt to their users'
preferences over a large set of all possible tasks that they can perform. This includes …

Previous work on preference learning focuses extensively on using rewards as proxies.
Despite fitting into the reinforcement learning paradigm nicely, reward-based machine …

Robots must learn how to behave in accordance with human desires and values. While
today's robot learning algorithms increasingly enable people to teach robots via diverse …

As assistive agents become increasingly ubiquitous in home environments, it is ever more
important that they are designed to operate within the preferences of the humans around …