263 search results - page 2 / 53 » Regret Bounds for Prediction Problems |
JMLR
2012
11 years 10 months ago
2012
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
COCOON
2006
Springer
13 years 11 months ago
2006
Springer
Abstract. While the complexity of min-max and min-max regret versions of most classical combinatorial optimization problems has been thoroughly investigated, there are very few stu...
ALT
2007
Springer
14 years 4 months ago
2007
Springer
Algorithms based on upper-confidence bounds for balancing exploration and exploitation are gaining popularity since they are easy to implement, efficient and effective. In this p...
JMLR
2010
13 years 2 months ago
2010
Bandit algorithms are concerned with trading exploration with exploitation where a number of options are available but we can only learn their quality by experimenting with them. ...
ECCC
2010
13 years 7 months ago
2010
Suppose a decision maker has to purchase a commodity over time with varying prices and demands. In particular, the price per unit might depend on the amount purchased and this pri...