Cooperative multi-agent reinforcement learning (MARL) requires agents to explore to learn to cooperate. Existing value-based MARL algorithms commonly rely on random exploration, such as $\epsilon$-greedy, which is inefficient in discovering multi-agent cooperation. Additionally, the environment in MARL appears non-stationary to any individual agent due to the simultaneous training of other agents, leading to highly variant and thus unstable optimisation signals. In this work, we propose ensemble value functions for multi-agent exploration (EMAX), a general framework to extend any value-based MARL algorithm. EMAX trains ensembles of value functions for each agent to address the key challenges of exploration and non-stationarity: (1) The uncertainty of value estimates across the ensemble is used in a UCB policy to guide the exploration of agents to parts of the environment which require cooperation. (2) Average value estimates across the ensemble serve as target values. These targets exhibit lower variance compared to commonly applied target networks and we show that they lead to more stable gradients during the optimisation. We instantiate three value-based MARL algorithms with EMAX, independent DQN, VDN and QMIX, and evaluate them in 21 tasks across four environments. Using ensembles of five value functions, EMAX improves sample efficiency and final evaluation returns of these algorithms by 54%, 55%, and 844%, respectively, averaged all 21 tasks.

翻译：协同多智能体强化学习要求智能体通过探索来学习合作。现有基于价值的MARL算法通常依赖随机探索（如ε-贪心），但在发现多智能体合作方面效率低下。此外，由于其他智能体同时训练，MARL环境对任意单个智能体呈现非平稳性，导致优化信号高度变化且不稳定。本文提出多智能体探索的集成价值函数框架（EMAX），该通用框架可扩展任意基于价值的MARL算法。EMAX为每个智能体训练集成价值函数，以应对探索与非平稳性两大关键挑战：（1）利用集成中价值估计的不确定性构建UCB策略，引导智能体探索需要合作的环境区域；（2）将集成平均价值估计作为目标值。相较常用目标网络，这些目标值方差更低，且能提供更稳定的优化梯度。我们使用EMAX实例化三种基于价值的MARL算法——独立DQN、VDN和QMIX，在四个环境的21个任务中评估。采用五个价值函数的集成时，EMAX分别将这些算法的样本效率和最终评估回报平均提升54%、55%和844%（基于全部21个任务）。