In this article, we propose a method to adapt stepsize parameters used in reinforcement learning for dynamic environments. In general reinforcement learning situations, a stepsize...
Perfect recall is the common and natural assumption that an agent never forgets. As a consequence, the agent can always condition its choice of action on any prior observations. I...
Kevin Waugh, Martin Zinkevich, Michael Johanson, M...
We develop strategy/false-name-proof multi-unit auction protocols for non-quasi-linear utilities. One almost universal assumption in auction theory literature is that each bidder ...
By feeding personal e-mails into the training set, personalized content-based spam filters are believed to classify e-mails in higher accuracy. However, filters trained by both sp...
The recent emergence of location-based social networking services is revolutionizing web-based social networking allowing users to share real-life experiences via geo-tagged user-...