Accepted Paper “Distributed Value Function Approximation for Collaborative Multi-Agent Reinforcement Learning"
02.2021
M. S. Stankovic, M. Beko, S. S. Stankovic, “Distributed Value Function Approximation for Collaborative Multi-Agent Reinforcement Learning", in IEEE Transactions on Control of Network Systems, doi.org/10.1109/TCNS.2021.3061909
