Abstract: In the centralized training and decentralized execution(CTDE) framework, agents can access the global state during training, but update their policies independently. This results in environmental non-stationarity, which degrades decision-making performance in certain states. Additionally, experience replay is commonly adopted to reduce sample correlation, but it may lead to insufficient sampling of certain states, resulting in poor decision-making performance. These issues reduce the robustness of decision-making in multi-agent deep reinforcement learning. To address these issues, an ensemble-based multi-agent deep reinforcement learning method is proposed. The proposed method integrates multiple policy or action-value networks to enhance decision robustness. When one network performs poorly in a particular state, decisions can still be made based on other effective networks. Two integration strategies, namely confidence-weighted action selection and action voting, are proposed to effectively combine outputs from multiple networks. The proposed approach demonstrates strong applicability in multi-agent deep reinforcement learning and applies to both actor-critic and value-based methods. Experiments were conducted in three environments by comparing the proposed method with six representative approaches. The results show that, when applied to the mainstream actor-critic algorithm MADDPG and the value decomposition method QMIX, the proposed method increases the win rate of the multi-agent system by 50%, and improves the maximum reward by 40.