Author Archives: decide_web

Published paper in IEEE Transactions on Control of Network Systems!

Paper “Distributed Value Function Approximation for Collaborative Multi-Agent Reinforcement Learning“, by M.S. Stanković, M. Beko and S.S. Stanković, has been published in IEEE Transactions on Control of Network Systems (IEEE TCNS)!

In the paper, several new distributed gradient-based temporal difference algorithms for decentralized multi-agent off-policy learning of the value function in Markov decision processes were proposed, rigorously theoretically analyzed and verified using extensive simulations.

Published paper in journal Sensors!

Paper “Distributed Spectrum Management in Cognitive Radio Networks by Consensus-Based Reinforcement Learning“, by D. Dašić, N. Ilić, M. Vučetić, M. Perić, M. Beko and M.S. Stanković, has been published in journal Sensors!

In the paper, the authors proposed a new algorithm for distributed spectrum management in Cognitive Radio Networks (CRN) based on a multi-agent reinforcement learning scheme. The paper presents a detailed discussion and analysis of the algorithm’s properties, together with extensive simulations illustrating the effectiveness and advantages of the proposed scheme.