2 search results - page 1 / 1 » Contextual Bandit Learning with Predictable Rewards |
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...
CORR
2011
Springer
12 years 11 months ago
2011
Springer
We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as...