In human-robot interaction or more generally multi-agent systems, we often have decentralized agents that need to perform a task together. In such settings, it is crucial to have the ability to anticipate the actions of other agents. Without this ability, the agents are often doomed to perform very poorly. Humans are usually good at this, and it is mostly because we can have good estimates of what other agents are trying to do. We want to give such an ability to robots through reward learning and partner modelling. In this seminar, Erdem will talk about active learning approaches to this problem and how we can leverage preference data to learn objectives. Erdem will also show how preferences can help reward learning in the settings where demonstration data may fail, and how partner-modelling enables decentralized agents to cooperate efficiently.
About the Aerodynamics & Control Seminar Series
The Aerodynamics & Control Seminars, hosted by the Department of Aeronautics, are a series of talks by internationally renowned academics covering a broad range of topics in fluid mechanics, control, and the intersection of these two areas.