4345 search results - page 311 / 869 » Relational Reinforcement Learning |
133
Voted
ICANN
2005
Springer
15 years 10 months ago
2005
Springer
Abstract. In practice, almost all control systems in use today implement some form of linear control. However, there are many tasks for which conventional control engineering metho...
143
Voted
ATAL
2004
Springer
15 years 10 months ago
2004
Springer
Single-agent reinforcement learners in time-extended domains and multi-agent systems share a common dilemma known as the credit assignment problem. Multi-agent systems have the st...
119
click to vote
BIOADIT
2004
Springer
15 years 10 months ago
2004
Springer
Abstract. How can artificial or natural agents autonomously gain understanding of its own internal (sensory) state? This is an important question not just for physically embodied ...
137
click to vote
ECML
2003
Springer
15 years 10 months ago
2003
Springer
Abstract. Distributed heterogeneous search environments are an emerging phenomenon in Web search, in which topic-specific search engines provide search services, and metasearchers...
162
Voted
DEXAW
1999
IEEE
15 years 9 months ago
1999
IEEE
This paper presents two metrics for the Nearest Neighbor Classifier that share the property of being adapted, i.e. learned, on a set of data. Both metrics can be used for similari...