Overview
- Presents advances in Ad Hoc Teamwork and Cooperation with Unknown Agents
- Devoted to the area of ad hoc teamwork in which an agent may potentially cooperate with a variety of teammates in order to achieve a shared goal
- Focuses on the three capabilities of ad hoc teamwork 1) robustness to teammate variety, 2) robustness to diverse tasks and 3) fast adaptation
- Includes supplementary material: sn.pub/extras
Part of the book series: Studies in Computational Intelligence (SCI, volume 603)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (8 chapters)
Keywords
About this book
This book is devoted to the encounter and interaction of agents such as robots with other agents and describes how they cooperate with their previously unknown teammates, forming an Ad Hoc team. It presents a new algorithm, PLASTIC, that allows agents to quickly adapt to new teammates by reusing knowledge learned from previous teammates. PLASTIC is instantiated in both a model-based approach, PLASTIC-Model and a policy-based approach, PLASTIC-Policy. In addition to reusing knowledge learned from previous teammates, PLASTIC also allows users to provide expert-knowledge and can use transfer learning (such as the new Two Stage Transfer algorithm) to quickly create models of new teammates when it has some information about its new teammates. The effectiveness of the algorithm is demonstrated on three domains, ranging from multi-armed bandits to simulated robot soccer games.
Authors and Affiliations
Bibliographic Information
Book Title: Making Friends on the Fly: Advances in Ad Hoc Teamwork
Authors: Samuel Barrett
Series Title: Studies in Computational Intelligence
DOI: https://doi.org/10.1007/978-3-319-18069-4
Publisher: Springer Cham
eBook Packages: Engineering, Engineering (R0)
Copyright Information: Springer International Publishing Switzerland 2015
Hardcover ISBN: 978-3-319-18068-7Published: 09 June 2015
Softcover ISBN: 978-3-319-36921-1Published: 09 October 2016
eBook ISBN: 978-3-319-18069-4Published: 25 May 2015
Series ISSN: 1860-949X
Series E-ISSN: 1860-9503
Edition Number: 1
Number of Pages: XX, 144
Number of Illustrations: 19 b/w illustrations, 7 illustrations in colour
Topics: Computational Intelligence, Game Theory, Economics, Social and Behav. Sciences, Data-driven Science, Modeling and Theory Building, Robotics and Automation, Artificial Intelligence