Artikel
Learning with minimal information in continuous games
While payoff-based learning models are almost exclusively devised for finite action games, where players can test every action, it is harder to design such learning processes for continuous games. We construct a stochastic learning rule, designed for games with continuous action sets, which requires no sophistication from the players and is simple to implement: players update their actions according to variations in own payoff between current and previous action. We then analyze its behavior in several classes of continuous games and show that convergence to a stable Nash equilibrium is guaranteed in all games with strategic complements as well as in concave games, while convergence to Nash occurs in all locally ordinal potential games as soon as Nash equilibria are isolated.
- Sprache
-
Englisch
- Erschienen in
-
Journal: Theoretical Economics ; ISSN: 1555-7561 ; Volume: 15 ; Year: 2020 ; Issue: 4 ; Pages: 1471-1508 ; New Haven, CT: The Econometric Society
- Klassifikation
-
Wirtschaft
Noncooperative Games
Search; Learning; Information and Knowledge; Communication; Belief; Unawareness
- Thema
-
Payoff-based learning
continuous games
stochastic approximation
- Ereignis
-
Geistige Schöpfung
- (wer)
-
Bervoets, Sebastian
Bravo, Mario
Faure, Mathieu
- Ereignis
-
Veröffentlichung
- (wer)
-
The Econometric Society
- (wo)
-
New Haven, CT
- (wann)
-
2020
- DOI
-
doi:10.3982/TE3435
- Handle
- Letzte Aktualisierung
-
10.03.2025, 11:41 MEZ
Datenpartner
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Objekttyp
- Artikel
Beteiligte
- Bervoets, Sebastian
- Bravo, Mario
- Faure, Mathieu
- The Econometric Society
Entstanden
- 2020
Ähnliche Objekte (12)
Asymmetric Information and Learning in Games
Game Forms with Minimal Strategy Spaces
Orientation Games and Minimal Ramsey Graphs
Continuous-time Games of Timing
Stopping Games in Continuous Time
Limits of minimal models and continuous orbifolds
A Minimal Continuous-Time Markov Pharmacometric Model
On the minimal representation of homogeneous games
Dynamical inspection game with continuous strategies
Learning continuous models for continuous physics
Supporting Learning in Information Systems by Facilitating Motivation with Games and Game Elements
Perceiving strategic environments: an experimental study of learning under minimal information
Asymmetric Information and Learning in Games
Game Forms with Minimal Strategy Spaces
Orientation Games and Minimal Ramsey Graphs
Continuous-time Games of Timing
Stopping Games in Continuous Time
Limits of minimal models and continuous orbifolds
A Minimal Continuous-Time Markov Pharmacometric Model
On the minimal representation of homogeneous games
Dynamical inspection game with continuous strategies
Learning continuous models for continuous physics
Supporting Learning in Information Systems by Facilitating Motivation with Games and Game Elements
Perceiving strategic environments: an experimental study of learning under minimal information
Asymmetric Information and Learning in Games
Game Forms with Minimal Strategy Spaces
Orientation Games and Minimal Ramsey Graphs
Continuous-time Games of Timing
Stopping Games in Continuous Time
Limits of minimal models and continuous orbifolds
A Minimal Continuous-Time Markov Pharmacometric Model
On the minimal representation of homogeneous games
Dynamical inspection game with continuous strategies
Learning continuous models for continuous physics
Supporting Learning in Information Systems by Facilitating Motivation with Games and Game Elements