We describe a generalized Q-learning type algorithm for reinforcement learning in competitive multi-agent games. We make the observation that in a competitive setting with adaptive...
Pieter Jan't Hoen, Sander M. Bohte, Han La Poutr&e...
—Millions of people are using the World Wide Web and are publishing content online. This user generated content contains many information relevant not only to marketing but to co...
Images are usually transmitted across the Internet using a lossless protocol such as TCP/IP. Lossless protocols require retransmission of lost packets, which substantially increas...
—Wireless ad hoc networks are connected to the fixed Internet by means of Internet gateways. Whenever a node within the ad hoc network wishes to communicate with a host in the I...