File:Derivate-follower-basin-of-attraction.png

Movement of a agent using Deterministic Reactive RL. By using derivative-Follower adaptation the agent stops prematurelly before attaining the highest profit/value.

Image taken from: Leigh Tesfatsion, Learning Algorithms: Illustrative Examples http://www.econ.iastate.edu/tesfatsi/LearnAlgorithms.LT.pdf