Access Restriction

Author Bozinovski, Stevo ♦ Bozinovska, Liljana
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Several Agent Architecture ♦ Rein-forcement Learning Theory ♦ Reinforcement Learning The-ory ♦ Delayed Reinforcement Learning ♦ Learn-ing Rule ♦ Ac-tor Critic Architecture ♦ Possible Implication ♦ Early Connectionist Agent Architecture ♦ Caa Architecture ♦ Clas-sical Drl Problem ♦ Connectionist Architec-tures
Abstract The DRL (Delayed Reinforcement Learning) problem is classical in Reinforcement Learning the-ory. There were several agent architectures solving that problem including some connectionist architec-tures. This work describes an early connectionist agent architecture, the CAA architecture, that solved the problem using the concept of emotion it its learn-ing rule. The architecture is compared to another clas-sical DRL problem solving architecture, the Ac-tor/Critic architecture. Possible implication to rein-forcement learning theory is pointed out.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study