Imagen de Portada

Online Learning for Uninformed Markov Games: Empirical Nash-Value Regret and Non-Stationarity Adaptation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Junyan, Luo, Haipeng, Zhang, Zihan, Ratliff, Lillian J.
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computer Science and Game Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback
por: Maiti, Arnab, et al.
Publicado: (2023)

Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality
por: Liu, Junyan, et al.
Publicado: (2025)

Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
por: Liu, Junyan, et al.
Publicado: (2025)

Proximal Regret and Proximal Correlated Equilibria: A New Tractable Solution Concept for Online Learning and Games
por: Cai, Yang, et al.
Publicado: (2025)

Convergence of Learning Dynamics in Stackelberg Games
por: Fiez, Tanner, et al.
Publicado: (2019)

Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
por: Cai, Yang, et al.
Publicado: (2023)

Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games
por: Dong, Jing, et al.
Publicado: (2024)

A Learning Algorithm That Attains the Human Optimum in a Repeated Human-Machine Interaction Game
por: Isa, Jason T., et al.
Publicado: (2025)

Corrupted Learning Dynamics in Games
por: Tsuchiya, Taira, et al.
Publicado: (2024)

Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries
por: Maiti, Arnab, et al.
Publicado: (2025)

No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
por: Zhang, Mengxiao, et al.
Publicado: (2024)

On Tractable $Φ$-Equilibria in Non-Concave Games
por: Cai, Yang, et al.
Publicado: (2024)

Query-Efficient Algorithm to Find all Nash Equilibria in a Two-Player Zero-Sum Matrix Game
por: Maiti, Arnab, et al.
Publicado: (2023)

Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
por: Zhang, Brian Hu, et al.
Publicado: (2025)

Do LLM Agents Have Regret? A Case Study in Online Learning and Games
por: Park, Chanwoo, et al.
Publicado: (2024)

Scale-Invariant Fast Convergence in Games
por: Tsuchiya, Taira, et al.
Publicado: (2026)

Convergence Analysis of Gradient-Based Learning with Non-Uniform Learning Rates in Non-Cooperative Multi-Agent Settings
por: Chasnov, Benjamin, et al.
Publicado: (2019)

Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games
por: Cai, Yang, et al.
Publicado: (2024)

Improved Regret Bounds for Online Fair Division with Bandit Learning
por: Schiffer, Benjamin, et al.
Publicado: (2025)

Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback
por: Ba, Wenjia, et al.
Publicado: (2021)

Optimistic Thompson Sampling for No-Regret Learning in Unknown Games
por: Li, Yingru, et al.
Publicado: (2024)

Regret Minimization and Convergence to Equilibria in General-sum Markov Games
por: Erez, Liad, et al.
Publicado: (2022)

Honor Among Bandits: No-Regret Learning for Online Fair Division
por: Procaccia, Ariel D., et al.
Publicado: (2024)

Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
por: Jordan, Philip, et al.
Publicado: (2026)

Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation
por: Gonzales, Jake, et al.
Publicado: (2026)

Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
por: Nguyen-Tang, Thanh, et al.
Publicado: (2024)

On the Universal Near Optimality of Hedge in Combinatorial Settings
por: Fan, Zhiyuan, et al.
Publicado: (2025)

Emergent specialization from participation dynamics and multi-learner retraining
por: Dean, Sarah, et al.
Publicado: (2022)

Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games
por: Nayak, Anupam, et al.
Publicado: (2025)

The Relationship between No-Regret Learning and Online Conformal Prediction
por: Ramalingam, Ramya, et al.
Publicado: (2025)

Last-Iterate Convergence of No-Regret Learning for Equilibria in Bargaining Games
por: Kamp, Serafina, et al.
Publicado: (2025)

Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
por: Maiti, Arnab, et al.
Publicado: (2026)

Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria
por: Barakat, Anas, et al.
Publicado: (2026)

Simultaneous Swap Regret Minimization via KL-Calibration
por: Luo, Haipeng, et al.
Publicado: (2025)

Approximating Nash Equilibria in General-Sum Games via Meta-Learning
por: Sychrovský, David, et al.
Publicado: (2025)

Regret Minimization in Stackelberg Games with Side Information
por: Harris, Keegan, et al.
Publicado: (2024)

Is Online Linear Optimization Sufficient for Strategic Robustness?
por: Cai, Yang, et al.
Publicado: (2026)

Learning not to Regret
por: Sychrovský, David, et al.
Publicado: (2023)

Computational Lower Bounds for Regret Minimization in Normal-Form Games
por: Anagnostides, Ioannis, et al.
Publicado: (2024)

Optimism Without Regularization: Constant Regret in Zero-Sum Games
por: Lazarsfeld, John, et al.
Publicado: (2025)