Results 11 to 20 of about 784,857 (332)
Quantum Extensive Form Games [PDF]
SSRN Electronic Journal, 2022 15 ...
Kazuki Ikeda
openaire +3 more sources
Polytope-form games and index/degree theories for extensive-form games [PDF]
Games and Economic Behavior, 2023 We present an index theory of equilibria for extensive form games. This requires developing an index theory for games where the strategy sets of players are general polytopes and their payoff functions are multiaffine in the product of these polytopes.
Lucas Pahl
openaire +4 more sources
Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games [PDF]
Neural Information Processing Systems, 2023 We introduce a new approach for computing optimal equilibria via learning in games. It applies to extensive-form settings with any number of players, including mechanism design, information design, and solution concepts such as correlated, communication,
B. Zhang +9 more
semanticscholar +1 more source
Regret-Minimizing Double Oracle for Extensive-Form Games [PDF]
International Conference on Machine Learning, 2023 By incorporating regret minimization, double oracle methods have demonstrated rapid convergence to Nash Equilibrium (NE) in normal-form games and extensive-form games, through algorithms such as online double oracle (ODO) and extensive-form double oracle
Xiaohang Tang +3 more
semanticscholar +1 more source
The Power of Regularization in Solving Extensive-Form Games [PDF]
International Conference on Learning Representations, 2022 In this paper, we investigate the power of {\it regularization}, a common technique in reinforcement learning and optimization, in solving extensive-form games (EFGs).
Ming Liu +3 more
semanticscholar +1 more source
Block-Coordinate Methods and Restarting for Solving Extensive-Form Games [PDF]
Neural Information Processing Systems, 2023 Coordinate descent methods are popular in machine learning and optimization for their simple sparse updates and excellent practical performance. In the context of large-scale sequential game solving, these same properties would be attractive, but until ...
D. Chakrabarti +2 more
semanticscholar +1 more source
Local and adaptive mirror descents in extensive-form games [PDF]
Neural Information Processing Systems, 2023 We study how to learn $\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback. In this setting, players update their policies sequentially based on their observations over a fixed number of episodes, denoted ...
Côme Fiegel +5 more
semanticscholar +1 more source
Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games [PDF]
Neural Information Processing Systems, 2022 For common notions of correlated equilibrium in extensive-form games, computing an optimal (e.g., welfare-maximizing) equilibrium is NP-hard. Other equilibrium notions -- communication (Forges 1986) and certification (Forges&Koessler 2005) equilibria ...
B. Zhang, T. Sandholm
semanticscholar +1 more source
Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games [PDF]
Neural Information Processing Systems, 2022 Imperfect-Information Extensive-Form Games (IIEFGs) is a prevalent model for real-world games involving imperfect information and sequential plays. The Extensive-Form Correlated Equilibrium (EFCE) has been proposed as a natural solution concept for multi-
Ziang Song, Song Mei, Yu Bai
semanticscholar +1 more source
Optimal Private Payoff Manipulation against Commitment in Extensive-form Games [PDF]
Workshop on Internet and Network Economics, 2022 To take advantage of strategy commitment, a useful tactic of playing games, a leader must learn enough information about the follower's payoff function.
Yurong Chen, Xiaotie Deng, Yuhao Li
semanticscholar +1 more source