Actor-Critic Fictitious Play in Simultaneous ...
Document type :
Communication dans un congrès avec actes
Title :
Actor-Critic Fictitious Play in Simultaneous Move Multistage Games
Author(s) :
Pérolat, Julien [Auteur]
Sequential Learning [SEQUEL]
Université de Lille, Sciences et Technologies
Piot, Bilal [Auteur]
IMS : Information, Multimodalité & Signal
Pietquin, Olivier [Auteur]
IMS : Information, Multimodalité & Signal
Sequential Learning [SEQUEL]
Université de Lille, Sciences et Technologies
Piot, Bilal [Auteur]
IMS : Information, Multimodalité & Signal
Pietquin, Olivier [Auteur]
IMS : Information, Multimodalité & Signal
Conference title :
AISTATS 2018 - 21st International Conference on Artificial Intelligence and Statistics
City :
Playa Blanca, Lanzarote, Canary Islands
Country :
Espagne
Start date of the conference :
2018-04-09
HAL domain(s) :
Informatique [cs]
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Intelligence artificielle [cs.AI]
English abstract : [en]
Fictitious play is a game theoretic iterative procedure meant to learn an equilibrium in normal form games. However, this algorithm requires that each player has full knowledge of other players' strategies. Using an ...
Show more >Fictitious play is a game theoretic iterative procedure meant to learn an equilibrium in normal form games. However, this algorithm requires that each player has full knowledge of other players' strategies. Using an architecture inspired by actor-critic algorithms, we build a stochastic approximation of the fictitious play process. This procedure is on-line, decentralized (an agent has no information of others' strategies and rewards) and applies to multistage games (a generalization of normal form games). In addition, we prove convergence of our method towards a Nash equilibrium in both the cases of zero-sum two-player multistage games and cooperative multistage games. We also provide empirical evidence of the soundness of our approach on the game of Alesia with and without function approximation.Show less >
Show more >Fictitious play is a game theoretic iterative procedure meant to learn an equilibrium in normal form games. However, this algorithm requires that each player has full knowledge of other players' strategies. Using an architecture inspired by actor-critic algorithms, we build a stochastic approximation of the fictitious play process. This procedure is on-line, decentralized (an agent has no information of others' strategies and rewards) and applies to multistage games (a generalization of normal form games). In addition, we prove convergence of our method towards a Nash equilibrium in both the cases of zero-sum two-player multistage games and cooperative multistage games. We also provide empirical evidence of the soundness of our approach on the game of Alesia with and without function approximation.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-01724227/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01724227/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01724227/file/AISTATS2018%20%2813%29.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- AISTATS2018%20%2813%29.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- AISTATS2018%20%2813%29.pdf
- Open access
- Access the document