IBM: games, A.I. & the future of cognitive computing
Published on Mar 7, 2016
Developing AI programs to master board games drove progress in the field — including advances in techniques for search algorithms and evaluation functions. However, research in such “clean” game domains did not really address most real-life tasks that have a "messy" nature. Real-world tasks typically pose additional challenges, such as ambiguous, hidden or missing data, and "non-stationarity," meaning that the task can change unexpectedly over time. IBM is now turning our attention to solving these real-world challenges.
IBM Research scientists Murray Campbell, Gerry Tesauro, and Eric Brown discuss "Extending Game-Based AI Research into the Wild.
"Extending Game-Based AI Research into the Wild"
by Steve Hamm
March 7, 2016
Социальные закладки