2664 search results - page 427 / 533 » The Many Faces of Agents |
152
click to vote
ECAI
2008
Springer
15 years 8 months ago
2008
Springer
In this paper, we propose a policy gradient reinforcement learning algorithm to address transition-independent Dec-POMDPs. This approach aims at implicitly exploiting the locality...
154
click to vote
CLIMA
2007
15 years 7 months ago
2007
Over the years, Logic Programming has proved to be a good and natural tool for expressing, querying and manipulating explicit knowledge in many areas of computer science. However, ...
154
click to vote
CLIMA
2007
15 years 7 months ago
2007
Abstract. Failures are unavoidable in many circumstances. For example, an agent may fail at some point to perform a task in a dynamic environment. Robust systems typically have mec...
154
click to vote
COMMA
2008
15 years 7 months ago
2008
In this paper we describe PADUA, a protocol designed to enable agents to debate an issue drawing arguments not from a knowledge base of facts, rules and priorities but directly fro...
170
click to vote
CATS
2006
15 years 7 months ago
2006
Learning from examples is an important characteristic feature of intelligence in both natural and artificial intelligent agents. In this paper, we study learnability of term rewri...