Dr. Santi Ontañón Villar, Researcher , Georgia Institute of Technology,
Cognitive Computing Lab

"Case-Based Planning for Real-Time Strategic Domains"

Monday, March 30, 2:00 PM

Packard Lab room 208

Reception prior to talk in Packard Lobby

Abstract: Some domains, such as real-time strategy (RTS) game, pose several challenges to traditional planning and machine learning techniques. In this talk, I will focus on how can those problems be addressed by using case-based planning techniques. In particular I will focus on the issues of plan acquisition, on-line plan execution, interleaved planning and execution and on-line plan adaptation. I will also introduce and demonstrate the Darmok system, which uses case-based planning to play strategy games.

Bio:Santiago Ontañón is a researcher at the Georgia Institute of Technology in the Cognitive Computing Lab directed by Professor Ashwin Ram. Dr. Ontañón  got his PhD in artificial intelligence in the Artificial Intelligence Research Institute (IIIA) in Barcelona, Spain. His main research areas is case-based reasoning (CBR) and specially  distributed case-based reasoning and the application of CBR techniques to computer games.
He is currently funded under DARPA's Transfer Learning program.