2011 search results - page 57 / 403 » Universal Reinforcement Learning |
171
click to vote
HIS
2004
15 years 5 months ago
2004
: This work presents a new hybrid neuro-fuzzy model for automatic learning of actions taken by agents. The main objective of this new model is to provide an agent with intelligence...
131
click to vote
LEGE
2003
15 years 5 months ago
2003
This paper presents experiences from the course of Informatics at the Hellenic Open University. Problems faced and lessons learned are presented relating to the
120
click to vote
CIVR
2007
Springer
15 years 10 months ago
2007
Springer
Fusion of multimedia streams for enhanced performance is a critical problem for retrieval. However, fusion performance tends to easily overfit the hillclimb set used to learn fus...
131
click to vote
ATAL
2003
Springer
15 years 9 months ago
2003
Springer
Much emphasis in multiagent reinforcement learning (MARL) research is placed on ensuring that MARL algorithms (eventually) converge to desirable equilibria. As in standard reinfor...
138
click to vote
IJCAI
2007
15 years 5 months ago
2007
We explore an application to the game of Go of a reinforcement learning approach based on a linear evaluation function and large numbers of binary features. This strategy has prov...