Best-Response Multiagent Learning in Non-Stationary Environments

This paper investigates a relatively new direction in Multiagent Reinforcement Learning. Most multiagent learning techniques focus on Nash equilibria as elements of both the learning algorithm and its evaluation criteria. In contrast, we propose a multiagent learning algorithm that is optimal in the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Autonomous Agents and Multiagent Systems: Proceedings, 3rd International Joint Conference, New York City, New York, 2004. s. 506 - 513
Hlavní autoři: Weinberg, Michael, Rosenschein, Jeffrey S.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: Washington, DC, USA IEEE Computer Society 19.07.2004
IEEE
Edice:ACM Conferences
Témata:
Algorithm design and analysis
Autonomous agents
Computer science
Computing methodologies > Artificial intelligence > Distributed artificial intelligence > Multi-agent systems
Computing methodologies > Artificial intelligence > Planning and scheduling
Computing methodologies > Machine learning > Learning paradigms
Computing methodologies > Machine learning > Machine learning approaches > Markov decision processes
Convergence
Game theory
Learning
Permission
Process control
Stochastic processes
Theory of computation > Theory and algorithms for application domains > Machine learning theory > Markov decision processes
ISBN:9781581138641, 1581138644
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper investigates a relatively new direction in Multiagent Reinforcement Learning. Most multiagent learning techniques focus on Nash equilibria as elements of both the learning algorithm and its evaluation criteria. In contrast, we propose a multiagent learning algorithm that is optimal in the sense of finding a best-response policy, rather than in reaching an equilibrium. We present the first learning algorithm that is provably optimal against restricted classes of non-stationary opponents. The algorithm infers an accurate model of the opponentýs non-stationary strategy, and simultaneously creates a best-response policy against that strategy. Our learning algorithm works within the very general framework of n-player, general-sum stochastic games, and learns both the game structure and its associated optimal policy.
Bibliografie:SourceType-Conference Papers & Proceedings-1
ObjectType-Conference Paper-1
content type line 25
ISBN:9781581138641
1581138644
DOI:10.5555/1018410.1018798