Results 261 to 270 of about 784,857 (332)

Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Extensive-Form Games

arXiv.org, 2023
A recent paper by Farina&Pipis (2023) established the existence of uncoupled no-linear-swap regret dynamics with polynomial-time iterations in extensive-form games.
B. Zhang, Gabriele Farina, T. Sandholm
semanticscholar   +1 more source

Logit Learning by Valuation in Extensive-Form Games with Simultaneous Moves

IEEE Conference on Decision and Control, 2023
We study the long-term behavior of the logit learning rule in multiplayer repeated extensive-form games. Our model involves the possibility of simultaneous moves by multiple players as well as chance moves by nature in every node of the game tree.
Jason Castiglione, Gürdal Arslan
semanticscholar   +1 more source

Multiplicative Weight Updates for Extensive Form Games

Adaptive Agents and Multi-Agent Systems, 2023
Recent research in Nash equilibrium (NE) computation in extensive forms games (EFGs), such as poker, show that it is possible to compute strong solutions for two-player zero-sum games via regret minimization in theory and practice. Regret minimization is
Chirag Chhablani   +2 more
semanticscholar   +1 more source

Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation

ACM Conference on Economics and Computation, 2022
We study the problem of finding optimal correlated equilibria of various sorts: normal-form coarse correlated equilibrium (NFCCE), extensive-form coarse correlated equilibrium (EFCCE), and extensive-form correlated equilibrium (EFCE).
B. Zhang   +3 more
semanticscholar   +1 more source

Responsibility in Extensive Form Games

AAAI Conference on Artificial Intelligence, 2023
Two different forms of responsibility, counterfactual and seeing-to-it, have been extensively discussed in philosophy and AI in the context of a single agent or multiple agents acting simultaneously.
Qi Shi
semanticscholar   +1 more source

EFDO: Solving Extensive-Form Games Based On Double Oracle

International Conference on Data Intelligence and Security, 2022
Although algorithm like counterfactual regret minimization (CFR) proved to be effective in small games, the demands on computing and storage resources limits its application among large EFGs. We propose a new algorithm called extensive-form double oracle
Song Qin   +6 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy