IFlowNets make generative flow networks work for imperfect-information games by adding an information-set aggregation constraint that restores valid flow matching.
(2024), by constructionF 1(z) =R 1(z) andF 2(z) =R 2(z) for allz∈Z, soF(z) def.=F 1(z)F2(z) C1=R 1(z)R2(z) for allz∈Z
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.