82 search results - page 4 / 17 » Balancing Exploration and Exploitation in Learning to Rank O... |
EMNLP
2007
14 years 11 months ago
2007
Many emerging applications require documents to be repeatedly updated. Such documents include newsfeeds, webpages, and shared community resources such as Wikipedia. In this paper ...
99
Voted
NN
2002
Springer
14 years 10 months ago
2002
Springer
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
69
Voted
GECCO
2007
Springer
15 years 4 months ago
2007
Springer
Imagine a group of cooperating agents attempting to allocate tasks amongst themselves without knowledge of their own capabilities. Over time, they develop a belief of their own sk...
69
Voted
ICRA
2010
IEEE
14 years 8 months ago
2010
IEEE
— Sampling-based kinodynamic planners, such as the popular RRT algorithm, have been proposed as promising solutions to planning for systems with dynamics. Nevertheless, complex s...
89
Voted
ICML
2005
IEEE
15 years 11 months ago
2005
IEEE
We present an efficient "sparse sampling" technique for approximating Bayes optimal decision making in reinforcement learning, addressing the well known exploration vers...