Abstract
The problem addressed in this article is that of automatical ly designing autonomous agents having to solve complex tasks involving several -andpossibly concurrent- objectives. We propose a modular approach based on the principles of acti on selection where the actions recommanded by several basic behaviors are combined in a glo bal decision. In this framework, our main contribution is a method making an agent able to auto matically define and build the basic behaviors it needs through incremental reinforcemen t learning methods. This way, we obtain a very autonomous architecture requiring very few ha nd-coding. This approach is tested and discussed on a representative problem taken from the ti le-world.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
