paper-with-me

홈 › Papers

Second-Order Mirror Descent: Convergence in Games Beyond Averaging and Discounting

2021-11-18 · Bolin Gao, Lacra Pavel

In this paper, we propose a second-order extension of the continuous-time game-theoretic mirror descent (MD) dynamics, referred to as MD2, which provably converges to mere (but not necessarily strict) variationally stable states (VSS) without using common auxiliary techniques such as time-averaging or discounting. We show that MD2 enjoys no-regret as well as an exponential rate of convergence towards strong VSS upon a slight modification. MD2 can also be used to derive many novel continuous-time primal-space dynamics. We then use stochastic approximation techniques to provide a convergence guarantee of discrete-time MD2 with noisy observations towards interior mere VSS. Selected simulations are provided to illustrate our results.

📄 PDF Abstract BibTeX arXiv:2111.09982

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games

2022-06-12 · Samuel Sokota, Ryan D'Orazio, J. Zico Kolter, Nicolas Loizou 외

This work studies an algorithm, which we call magnetic mirror descent, that is inspired by mirror descent and the non-Euclidean proximal gradient algorithm. Our contribution is demonstrating the virtues of magnetic mirro…

Deep Reinforcement LearningMuJoCo Gamesreinforcement-learningReinforcement Learning+1

Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games

2018-07-01 · ICML 2018 7 · Ehsan Asadi Kangarshahi, Ya-Ping Hsieh, Mehmet Fatih Sahin, Volkan Cevher

We revisit the problem of solving two-player zero-sum games in the decentralized setting. We propose a simple algorithmic framework that simultaneously achieves the best rates for honest regret as well as adversaria…

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes

2020-02-17 · Qi Lei, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang

In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games. Specifically, \cite{DISZ17, LiangS18} sh…

Generalized Mirror Descents in Congestion Games

2016-05-25 · Po-An Chen, Chi-Jen Lu

Different types of dynamics have been studied in repeated game play, and one of them which has received much attention recently consists of those based on "no-regret" algorithms from the area of machine learning. It is k…

Regret Matching+: (In)Stability and Fast Convergence in Games

2023-05-24 · NeurIPS 2023 11

Regret Matching+ (RM+) and its variants are important algorithms for solving large-scale games. However, a theoretical understanding of their success in practice is still a mystery. Moreover, recent advances on fast conv…