1. Value decomposition networks for cooperative multi-agent learning based on team reward;Sunehag
2. Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning;Rashid
3. Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning;Son
4. Qplex: Duplex dueling multi-agent q-learning;Wang
5. Celebrating Diversity in Shared Multi-Agent Reinforcement Learning;Li;Advances in Neural Information Processing Systems(NeurIPS),2021