492 search results - page 13 / 99 » A Failure to Learn from the Past |
AIIDE
2008
13 years 9 months ago
2008
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...
SIGOPS
2008
13 years 7 months ago
2008
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...
AIPS
2011
12 years 11 months ago
2011
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...
LAMAS
2005
Springer
14 years 26 days ago
2005
Springer
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...
AGI
2008
13 years 8 months ago
2008
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...