Learning to communicate with multi-agent reinforcement learning using value-decomposition networks

Vanneste, SimonSimonVannesteVanneste, AstridAstridVannesteBosmans, StigStigBosmansMercelis, SiegfriedSiegfriedMercelisHellinckx, PeterPeterHellinckx2021-10-272021-10-272019https://imec-publications.be/handle/20.500.12860/34326Learning to communicate with multi-agent reinforcement learning using value-decomposition networksProceedings paperhttps://doi.org/10.1007/978-3-030-33509-0_69