Reactive bandits with attitude
JMLR Workshop and Conference Proceedings, pp. 726-734, 2015.
We consider a general class of K-armed bandits that adapt to the actions of the player. A single continuous parameter characterizes the "attitude" of the bandit, ranging from stochastic to cooperative or to fully adversarial in nature. The player seeks to maximize the expected return from the adaptive bandit, and the associated optimizati...More
PPT (Upload PPT)