Browsing Division of Electrical, Electronics, and Computer Science (EECS) by Subject "linear bandits"
Now showing items 1-2 of 2
-
Algorithms for Online Learning in Structured Environments
Online learning deals with the study of making decisions sequentially using information gathered along the way. Typical goals of an online learning agent can be to maximize the reward gained during learning or to identify ... -
Exploration and Misspecification in Reinforcement Learning
Among the basic challenges that confront reinforcement learning are exploration – the need to search effectively over large and complex state-action spaces – and misspecification, which arises from using function ...