IFlowNets make generative flow networks work for imperfect-information games by adding an information-set aggregation constraint that restores valid flow matching.
Expected flow networks in stochastic environments and two-player zero-sum games
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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) 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.
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games
IFlowNets make generative flow networks work for imperfect-information games by adding an information-set aggregation constraint that restores valid flow matching.