The paper presents an uncoupled learning algorithm, higher-order optimism with discounting (HOOD), for arbitrary N-player normal form games with up to K actions per player. HOOD achieves an individual regret bound of O(N³ log² K) uniformly over the play horizon by combining a discounted (N+1)-th order predictor with entropic regularization over a lifted strategy space. This design mitigates large oscillations in play, addressing a key challenge in prior attempts to attain constant regret in general games.
By Omar Abbadi, Rida Laraki, Panayotis Mertikopoulos
arXiv:2609.21976v1 Announce Type: cross
Abstract: We introduce Multiplicatively Optimistic Regret Matching (MORM), an uncoupled learning rule for finite general-sum games. Under simultaneous full-inf...
By Ashkan Soleymani, Georgios Piliouras
arXiv:2609.22839v1 Announce Type: cross
Abstract: Can simple learning rules keep their regret bounded in self-play? Recent work achieves constant regret bounds through modified regularization and hig...
By Junsoo Ha
arXiv:2609.16751v2 Announce Type: replace-cross
Abstract: We give deterministic and uncoupled learning dynamics for finite multiplayer general-sum games under full-information feedback that achieve c...
By Tung Mai
arXiv:2609. 16751v1 Announce Type: cross Abstract: We give deterministic and uncoupled learning dynamics for finite multiplayer general-sum games under full-information feedback that achieve constant individual swap regret, independent of the horizon $T$.
By Tung Mai
We give deterministic and uncoupled learning dynamics for finite multiplayer general-sum games under full-information feedback that achieve constant individual swap regret, independent of the horizon...
arXiv:2608. 04149v1 Announce Type: cross Abstract: Swap regret governs the rate at which uncoupled learning dynamics converge to correlated equilibria in multiplayer general-sum games.
By Taira Tsuchiya
arXiv:2610.00911v1 Announce Type: new
Abstract: We study an endogenous nonstationary stochastic bandit problem with latent linear dynamics, where actions affect both immediate rewards and the future...
By Taehyun Hwang, Hyunjun Choi, Heesang Ann, Min-hwan Oh
arXiv:2608. 09501v1 Announce Type: new Abstract: We consider the extensive-form bandit problem where on each trial the learner plays an extensive-form game against an oblivious adversary.
By Stephen Pasteris, Rahul Savani, Theodore Turocy
arXiv:2606. 02363v1 Announce Type: new Abstract: We study sequential decision-making in partially observable environments against strategic, adaptive opponents, modeled as partially observable Markov games (POMGs).
By Raman Arora
The paper presents an efficient algorithm for repeated prophet inequalities with prefix feedback, achieving “~O(√T) expected regret”. It uses empirical backward induction, box‑specific reach bonuses, and a relative‑drop aggregation rule to eliminate polynomial dependence on the number of boxes. This resolves an open question from Liu et al. (2025).
By Kun Wang
arXiv:2602.10727v3 Announce Type: replace
Abstract: Rising Multi-Armed Bandits (RMABs) model sequential decision problems where each arm's expected reward improves with repeated pulls. In such proble...
By Seockbean Song, Chenyu Gan, Youngsik Yoon, Siwei Wang, Wei Chen, Jungseul Ok