2020/09/04 by van Leeuwen, Cornelis Jan, Pawełczak, Przemyzław
#Artificial Intelligence (cs.AI) #Distributed #FOS: Computer and information sciences #Multiagent Systems (cs.MA) #Parallel #and Cluster Computing (cs.DC)
paper · doi:10.48550/arxiv.2009.02240
We propose a novel method for expediting both symmetric and asymmetric Distributed Constraint Optimization Problem (DCOP) solvers. The core idea is based on initializing DCOP solvers with greedy fast non-iterative DCOP solvers. This is contrary to existing methods where initialization is always achieved using a random value assignment. We empirically show that changing the starting conditions of existing DCOP solvers not only reduces the algorithm convergence time by up to 50%, but also reduces the communication overhead and leads to a better solution quality. We show that this effect is due to structural improvements in the variable assignment, which is caused by the spreading pattern of DCOP algorithm activation.) /Subject (Hybrid DCOPs)