Type of Document Master's Thesis Author Gadre, Aditya Shrikant Author's Email Address firstname.lastname@example.org URN etd-12142001-002614 Title Learning Strategies in Multi-Agent Systems - Applications to the Herding Problem Degree Master of Science Department Electrical and Computer Engineering Advisory Committee
Advisor Name Title Kachroo, Pushkin Committee Chair Saunders, William R. Committee Member VanLandingham, Hugh F. Committee Member Keywords
- Idiotopic Network
- Reinforcement Learning
- Reward functions
- Dynamic Programming
- Artificial Immune System
Date of Defense 2001-11-30 Availability unrestricted Abstract
"Multi-Agent systems" is a topic for a lot of research, especially research involving strategy, evolution and cooperation among various agents. Various learning algorithm schemes have been proposed such as reinforcement learning and evolutionary computing.
In this thesis two solutions to a multi-agent herding problem are presented. One solution is based on Q-learning algorithm, while the other is based on modeling of artificial immune system.
Q-learning solution for the herding problem is developed, using region-based local learning for each individual agent. Individual and batch processing reinforcement algorithms are implemented for non-cooperative agents. Agents in this formulation do not share any information or knowledge. Issues such as computational requirements, and convergence are discussed.
An idiotopic artificial immune network is proposed that includes individual B-cell model for agents and T-cell model for controlling the interaction among these agents. Two network models are proposed--one for evolving group behavior/strategy arbitration and the other for individual action selection.A comparative study of the Q-learning solution and the immune network solution is done on important aspects such as computation requirements, predictability, and convergence.
Filename Size Approximate Download Time (Hours:Minutes:Seconds)
28.8 Modem 56K Modem ISDN (64 Kb) ISDN (128 Kb) Higher-speed Access Thesis.pdf 1.95 Mb 00:09:02 00:04:38 00:04:03 00:02:01 00:00:10
If you have questions or technical problems, please Contact DLA.