Expected flow networks in stochastic environments and two-player zero-sum games
Mila/Université de Montréal · Mila - Quebec AI Institute · MILA · Montreal institute for learning algorithms (Mila) · Mila, University of Montreal · Mila / Université de Montréal
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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. Code: https://github.com/GFNOrg/AdversarialFlowNetworks.