ENGLISH

Sample Efficient Multiagent Learning in the Presence of Markovian Agents

By Doran Chakraborty (auth.)

Book information

Publisher
Springer International Publishing
Year
2014
ISBN
978-3-319-02605-3, 978-3-319-02606-0
DOI
10.1007/978-3-319-02606-0
Language
english
Format
PDF
Filesize
1 MB (1565783 bytes)
Series
Studies in Computational Intelligence 523
Edition
1
Pages
147\151
Orientation
yes
Scanned
yes
Time added
2013-10-06 15:58:03
Computational Intelligence; Artificial Intelligenc

Description

The problem of Multiagent Learning (or MAL) is concerned with the study of how intelligent entities can learn and adapt in the presence of other such entities that are simultaneously adapting. The problem is often studied in the stylized settings provided by repeated matrix games (a.k.a. normal form games). The goal of this book is to develop MAL algorithms for such a setting that achieve a new set of objectives which have not been previously achieved. In particular this book deals with learning in the presence of a new class of agent behavior that has not been studied or modeled before in a MAL context: Markovian agent behavior. Several new challenges arise when interacting with this particular class of agents. The book takes a series of steps towards building completely autonomous learning algorithms that maximize utility while interacting with such agents. Each algorithm is meticulously specified with a thorough formal treatment that elucidates its key theoretical properties.

Similar books