2 search results - page 1 / 1 » Contextual Bandit Learning with Predictable Rewards |
JMLR
2012
11 years 7 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 8 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...