Generative flow networks (GFlowNets) are sequential sampling models trained to match a given distribution. GFlowNets have been successfully applied to various structured object generation tasks, sampling a diverse set of high-reward objects quickly. We propose expected flow networks (EFlowNets), which extend GFlowNets to stochastic environments. We show that EFlowNets outperform other GFlowNet formulations in stochastic tasks such as protein design. We then extend the concept of EFlowNets to adversarial environments, proposing adversarial flow networks (AFlowNets) for two-player zero-sum games. We show that AFlowNets learn to find above 80% of optimal moves in Connect-4 via self-play and outperform AlphaZero in tournaments.

翻译：生成式流网络（GFlowNets）是一类为匹配给定分布而训练的序列采样模型。GFlowNets已成功应用于多种结构化对象生成任务，能够快速采样多样化的高奖励对象。我们提出期望流网络（EFlowNets），将GFlowNets扩展至随机环境。实验表明，在蛋白质设计等随机任务中，EFlowNets的表现优于其他GFlowNet变体。随后，我们将EFlowNets的概念扩展至对抗环境，提出用于双人零和博弈的对抗流网络（AFlowNets）。研究表明，AFlowNets通过自我对弈能学习到Connect-4游戏中超过80%的最优走法，并在锦标赛中击败AlphaZero。