collaborators

11 papers

cs.GT2026

Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization

Taira Tsuchiya

Swap regret governs the rate at which uncoupled learning dynamics converge to correlated equilibria in multiplayer general-sum games. Under full-information feedback, the best prev…

cs.GT2026

Scale-Invariant Fast Convergence in Games

Taira Tsuchiya, Haipeng Luo, Shinji Ito

Scale-invariance in games has recently emerged as a widely valued desirable property. Yet, almost all fast convergence guarantees in learning in games require prior knowledge of th…

cs.LG2026

Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret

Shinji Ito, Haipeng Luo, Arnab Maiti +2

Learning to play zero-sum games is a fundamental problem in game theory and machine learning. While significant progress has been made in minimizing external regret in the self-pla…

cs.LG2025

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback

Shinji Ito, Kevin Jamieson, Haipeng Luo +2

We study online learning in finite-horizon episodic Markov decision processes (MDPs) under the challenging aggregate bandit feedback model, where the learner observes only the cumu…

cs.LG2025

Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games

Taira Tsuchiya

In two-player zero-sum games, the learning dynamic based on optimistic Hedge achieves one of the best-known regret upper bounds among strongly-uncoupled learning dynamics. With an…

cs.LG2025

Reinforcement Learning from Adversarial Preferences in Tabular MDPs

Taira Tsuchiya, Shinji Ito, Haipeng Luo

We introduce a new framework of episodic tabular Markov decision processes (MDPs) with adversarial preferences, which we refer to as preference-based MDPs (PbMDPs). Unlike standard…