Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Restless bandits: Exploring and exploiting in a changing environment

Rather than reasoning about fully described decision problems, we often
have to learn to make decisions by taking actions and experiencing
their outcomes. In such situations, there is a dilemma between
choosing alternatives that we believe will provide good outcomes
("exploiting") and choosing alternatives in order to learn more about
their outcomes ("exploring"). How to balance exploration and
exploitation is a fundamental issue in reinforcement learning and
especially pertinent in volatile environments where the action-outcome
contingencies change over time. I will present two studies investigating
how people learn and make decisions in "restless bandit" tasks involving
repeated choices between multiple alternatives with changing
rewards, with a particular focus on the role of uncertainty in

Host: Konstantinos Tsetsos