Reinforcement Learning for P2P Searching

Abstract

For a peer-to-peer (P2P) system holding massive amount of data, an efficient and scalable search for resource sharing is a key determinant to its practical usage. Unstructured P2P networks avoid the limitations of centralized systems and the drawbacks of a highly structured approach, because they impose few constraints on topology and data placement, and they support highly versatile search mechanisms. However their search algorithms are usually based on simple flooding schemes, showing severe inefficiencies. In this paper, to address this major limitation, we propose and evaluate the adoption of a local adaptive routing protocol. The routing algorithm adopts a simple Reinforcement Learning scheme (driven by query interactions among neighbors), in order to dynamically adapt the topology to peer interests. Preliminaries evaluations show that the approach is able to dynamically group peer nodes in clusters containing peers with shared interests and organized into a small world network.