Title
Autonomous parsing of behavior in a multi-agent setting Autonomous parsing of behavior in a multi-agent setting
Author
Faculty/Department
Faculty of Applied Economics
Publication type
conferenceObject
Publication
S.l. , [*]
Subject
Computer. Automation
Source (book)
Proceedings of the 9th International Conference on Artificial Intelligence and Soft Computing
Carrier
E
Target language
English (eng)
Full text (Publishers DOI)
Abstract
Imitation learning is a promising route to instruct robotic multi-agent systems. However, imitating agents should be able to decide autonomously what behavior, observed in others, is interesting to copy. Here we investigate whether a simple recurrent network (Elman Net) can be used to extract meaningful chunks from a continuous sequence of observed actions. Results suggest that, even in spite of the high level of task specific noise, Elman nets can be used for isolating re-occurring action patterns in robots. Limitations and future directions are discussed.