Recent approaches to learning structured predictors often require approximate inference for tractability; yet its effects on the learned model are unclear. Meanwhile, most learnin...
Finding good representations of text documents is crucial in information retrieval and classification systems. Today the most popular document representation is based on a vector ...
Stochastic games are a generalization of MDPs to multiple agents, and can be used as a framework for investigating multiagent learning. Hu and Wellman (1998) recently proposed a m...
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
Increasingly systems are composed of parts: software components, and the interaction mechanisms (connectors) that enable them to communicate. When assembling systems from independ...