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.
arXiv:2608. 31166v1 Announce Type: new Abstract: Uncoupled no-regret dynamics provide a decentralized route to equilibrium, but prior guarantees for individual regret retain a polylogarithmic dependence on the horizon.
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...
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...
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...
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 $T$.
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: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...
The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
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.
arXiv:2608. 09389v1 Announce Type: cross Abstract: This note aims to serve as an entry point to the literature on learning in games, a topic with significant theoretical appeal and a wide range of applications -- from machine learning and data science to economics and beyond.
arXiv:2607. 08012v1 Announce Type: cross Abstract: This paper studies an online variant of the assistance games framework, where an informed agent and an uninformed agent repeatedly interact over $T$ timesteps to optimize a common reward function.
arXiv:2609.13547v1 Announce Type: new Abstract: We study switching regret in adversarial multi-armed bandits, where the learner competes with an arm sequence that changes at most $S$ times. When $S$...