What evolutionary game theory tells us about multiagent learning
By Karl Tuyls, Simon Parsons. 2007
161 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Management Science and Operations Research, Sociology and Political Science
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Karl Tuyls
- Marc Lanctot
- Julien Pérolat
- R´emi Munos
- Jean-Baptiste Lespiau
- Shayegan Omidshafiei
- Audrunas Gruslys
- Gerhard Weiss
In Management Science and Operations Research
- Karl Tuyls
- Marc Lanctot
- Julien Pérolat
- Gerhard Weiss
- Daan Bloembergen
- R´emi Munos
- Kagan Tumer
- Mitchell K. Colby
In Sociology and Political Science
- Ana Lúcia Cetertich Bazzan
- Daan Bloembergen
- Kagan Tumer
- Mitchell K. Colby
- Michael Kaisers
- Daniel Hennes
- Gerhard Weiss
- Karl Tuyls
Citations in the corpus
- Multiagent Learning: Basics, Challenges, and Prospects (2012, background): “Critical reflections of this classification can be for instance found in Stone (2007) and Tuyls and Parsons (2007).”
- Evolutionary Dynamics of Multi-Agent Learning: A Survey (2015, background): “In response, Tuyls and Parsons (2007) argue in favour of evolutionary game theory, rather than classical game theory, as the preferable framework within which to study multiagent learning formally.”
- Multiagent learning in the presence of memory-bounded agents (2013, unknown): “There has also been a significant volume of research in MAL that uses Q-learning as the base learning algorithm and does updates based on evolutionary methods, such as the model based on replicator dynamics [3,23,43].”
- Opportunities for multiagent systems and multiagent reinforcement learning in traffic control (2009, background): “348 Auton Agent Multi-Agent Syst (2009) 18:342–375 Also [ 83 ] discusses Shoham and etal.”
- Neural Replicator Dynamics (2019, background): “It has been suggested that enabling agents to adapt to nonstationary environments, rather than merely learn static policies, is the paramount objective in multiagent learning [54, 61].”
- An Evolutionary Game Theoretic Analysis of Difference Evaluation Functions (2015, background): “EGT is well suited as a model of cooperative coevolutionary algorithms, and thus provides a theoretical framework in which we can analyze the effects of different fitness assignment operators [6, 9, 10, 11, 13, 14].”