Expected flow networks in stochastic environments and two-player zero-sum games

arXiv:2310.02779v2 Announce Type: replace
Abstract: 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) …

abstract arxiv cs.gt cs.lg distribution diverse environments flow games generative match networks object objects sampling set stochastic tasks type