Abstract. Classical planning domain representations assume all the objects from one type are exactly the same. But when solving problems in the real world systems, the execution of...
The interest of graph matching techniques in the pattern recognition field is increasing due to the versatility of representing knowledge in the form of graphs. However, the size ...
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
Hugo Larochelle, Dumitru Erhan, Aaron C. Courville...
Combinatorial auctions (CAs) have emerged as an important model in economics and show promise as a useful tool for tackling resource allocation in AI. Unfortunately, winner determ...