Results 271 to 280 of about 784,857 (332)

A Lower Bound on Swap Regret in Extensive-Form Games

arXiv.org
Recent simultaneous works by Peng and Rubinstein [2024] and Dagan et al. [2024] have demonstrated the existence of a no-swap-regret learning algorithm that can reach $\epsilon$ average swap regret against an adversary in any extensive-form game within $m^
Constantinos Daskalakis, Gabriele Farina, Noah Golowich, T. Sandholm, B. Zhang   +4 more
semanticscholar   +1 more source

LiteEFG: An Efficient Python Library for Solving Extensive-form Games

arXiv.org
LiteEFG is an efficient library with easy-to-use Python bindings, which can solve multiplayer extensive-form games (EFGs). LiteEFG enables the user to express computation graphs in Python to define updates on the game tree structure.
Mingyang Liu, Gabriele Farina, A. Ozdaglar   +2 more
semanticscholar   +1 more source

On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games

Neural Information Processing Systems
First-order methods (FOMs) are arguably the most scalable algorithms for equilibrium computation in large extensive-form games. To operationalize these methods, a distance-generating function, acting as a regularizer for the strategy space, must be ...
Zhiyuan Fan, Christian Kroer, Gabriele Farina   +2 more
semanticscholar   +1 more source

Extensive Form Games

2019
There are other ways to represent games, and so we show how to adapt the coordinate system. (Readers more interested in normal form games with more players could jump ahead to the next chapter.) In a single-shot normal form game, it is standard to assume that each player makes their strategic choices simultaneously, or, at least, without knowledge of ...
Daniel T. Jessie, Donald G. Saari
openaire   +1 more source

RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning

International Conference on Machine Learning
Effective action abstraction is crucial in tackling challenges associated with large action spaces in Imperfect Information Extensive-Form Games (IIEFGs). However, due to the vast state space and computational complexity in IIEFGs, existing methods often
Boning Li, Zhixuan Fang, Longbo Huang
semanticscholar   +1 more source

Balancing risk and reward: CFRRA for extensive-form games

Other Conferences
In the field of game theory, rationality has traditionally been equated with the maximization of expected payoffs. However, in real-world scenarios, players often have different degrees of risk aversion, requiring a more suitable approach.
Yiyan Xu
semanticscholar   +1 more source

Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games

Neural Information Processing Systems
Recent breakthrough results by Dagan, Daskalakis, Fishelson and Golowich [2023] and Peng and Rubinstein [2023] established an efficient algorithm attaining at most $\epsilon$ swap regret over extensive-form strategy spaces of dimension $N$ in $N^{\tilde ...
B. Zhang, I. Anagnostides, Gabriele Farina, T. Sandholm   +3 more
semanticscholar   +1 more source

The Value of Recall in Extensive-Form Games

AAAI Conference on Artificial Intelligence
Imperfect-recall games—in which players may forget previously acquired information—have found many practical applications, ranging from game abstractions to team games and testing AI agents.
Ratip Emin Berker, Emanuel Tewolde, I. Anagnostides, T. Sandholm, Vincent Conitzer   +4 more
semanticscholar   +1 more source

Large extensive form games

Economic Theory, 2011
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Alós-Ferrer, Carlos, Ritzberger, Klaus
openaire   +4 more sources

Games in extensive form

2021
This chapter on games in extensive form is a convex combination of chapter III (on extensive-form decisions) and chapter X (on games in strategic form). We consider games of (nearly) perfect information without moves by nature.
openaire   +1 more source