Making Friends on the Fly: Advances in Ad Hoc Teamwork

Nonfiction, Science & Nature, Mathematics, Game Theory, Computers, Advanced Computing, Artificial Intelligence, General Computing
Cover of the book Making Friends on the Fly: Advances in Ad Hoc Teamwork by Samuel Barrett, Springer International Publishing
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Samuel Barrett ISBN: 9783319180694
Publisher: Springer International Publishing Publication: May 25, 2015
Imprint: Springer Language: English
Author: Samuel Barrett
ISBN: 9783319180694
Publisher: Springer International Publishing
Publication: May 25, 2015
Imprint: Springer
Language: English

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.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

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.

More books from Springer International Publishing

Cover of the book Tensor Network States and Effective Particles for Low-Dimensional Quantum Spin Systems by Samuel Barrett
Cover of the book New Trends in Databases and Information Systems by Samuel Barrett
Cover of the book Collaboration and Technology by Samuel Barrett
Cover of the book Derivative-Free and Blackbox Optimization by Samuel Barrett
Cover of the book Computational Science/Intelligence and Applied Informatics by Samuel Barrett
Cover of the book Growth Curve and Structural Equation Modeling by Samuel Barrett
Cover of the book The Franciscan Invention of the New World by Samuel Barrett
Cover of the book Wittgenstein, Mathematics and World by Samuel Barrett
Cover of the book Plasticity and Fracture by Samuel Barrett
Cover of the book The Complementarity Regime of the International Criminal Court by Samuel Barrett
Cover of the book Software Engineering Research, Management and Applications by Samuel Barrett
Cover of the book Biomaterials in Regenerative Medicine and the Immune System by Samuel Barrett
Cover of the book Magnetostatic Modelling of Thin Layers Using the Method of Moments And Its Implementation in OCTAVE/MATLAB by Samuel Barrett
Cover of the book Advances in Multimedia Information Processing -- PCM 2015 by Samuel Barrett
Cover of the book Formal Methods and Software Engineering by Samuel Barrett
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy