Emergent Consensus in Decentralised Systems Using Collaborative Reinforcement Learning

Abstract. This paper describes the application of a decentralised coordination algorithm, called Collaborative Reinforcement Learning (CRL), to two different distributed system problems. CRL enables the establishment of consensus between independent agents to support the optimisation of system-wide properties in distributed systems where there is no support for global state. Consensus between interacting agents on local environmental or system properties is established through localised advertisement of policy information by agents and the use of advertisements by agents to update their local, partial view of the system. As CRL assumes homogeneity in advertisement evaluation by agents, advertisements that improve the system optimisation problem tend to be propagated quickly through the system, enabling the system to collectively adapt its behaviour to a changing environment. In this paper, we describe the application of CRL to two different distributed system problems, a routing prot...

• Type: Conference
• Year: 2005
• Where: BERTINORO
• Authors: Jim Dowling, Raymond Cunningham, Anthony Harrington, Eoin Curran, Vinny Cahill
• Keywords: BERTINORO 2005, CRL Assumes Homogeneity, Distributed System, Information System, Optimisation Problem