This paper addresses the problem of plan recognition for multi-agent teams. Complex multi-agent tasks typically require dynamic teams where the team membership changes over time. ...
We present a new probabilistic framework for finding likely variable assignments in difficult constraint satisfaction problems. Finding such assignments is key to efficient sea...
Eric I. Hsu, Matthew Kitching, Fahiem Bacchus, She...
ADtrees, a data structure useful for caching sufficient statistics, have been successfully adapted to grow lazily when memory is limited and to update sequentially with an increme...
Robert Van Dam, Irene Langkilde-Geary, Dan Ventura
Symmetry is a widespread phenomenon that can offer opportunities for powerful exploitation in areas as diverse as molecular chemistry, pure mathematics, circuit design, biology an...
Off-policy reinforcement learning is aimed at efficiently reusing data samples gathered in the past, which is an essential problem for physically grounded AI as experiments are us...