Human experience with interactive games will be enhanced if the software agents that play the game learn from their failures. Techniques such as reinforcement learning provide one...
What do our computer systems do all day? How do we make sure they continue doing it when failures occur? Traditional approaches to answering these questions often involve inband m...
Dan Pelleg, Muli Ben-Yehuda, Richard Harper, Lisa ...
Engineering complete planning domain descriptions is often very costly because of human error or lack of domain knowledge. Learning complete domain descriptions is also very chall...
Use of tags to limit partner selection for playing has been shown to produce stable cooperation in agent populations playing the Prisoner’s Dilemma game. There is, however, a lac...
Understanding why the original project of Artificial Intelligence is widely regarded as a failure and has been abandoned even by most of contemporary AI research itself may prove c...