Emotion and Learning: Solving Delayed Reinforcement Learning Problem Using Emotionally Reinforced Connectionist Network

The DRL (Delayed Reinforcement Learning) problem is classical in Reinforcement Learning theory. There were several agent architectures solving that problem including some connectionist architectures. This work describes an early connectionist agent architecture, the CAA architecture, that solved the problem using the concept of emotion it its learning rule. The architecture is compared to another classical DRL problem solving architecture, the Actor/Critic architecture. Possible implication to reinforcement learning theory is pointed out.