Extend bounded regret beyond the current game and regret settings

Establish whether bounded regret can be achieved for broader classes of games and for stronger notions of regret, including swap regret, beyond arbitrary finite normal-form games with external regret.

Background

The main theorem concerns uncoupled full-information learning in arbitrary finite normal-form games and guarantees bounded external regret for every player. The paper does not resolve whether analogous uniformly bounded guarantees hold in broader classes of games or for stronger regret criteria such as swap regret; these are explicitly listed as future research directions.

References

Natural future research directions are whether this $\nPlayers2$ price can be reduced, whether the $\log2 \nPures$ dependence can be improved, and whether bounded regret is possible in broader game classes, and for stronger notions of regret, such as swap regret.

— Constant regret in general games via higher-order optimism  (2609.04113 - Abbadi et al., 3 Sep 2026) in Section 5, Concluding remarks