Because it allows the synthesis of behaviors despite theabsence of a robot-world interaction model, Q-learning hasbecome the most used learning algorithm for autonomousrobotics in applications such as obstacle avoidance, wallfollowing, go-to-the-nest, etc. This is mostly due toneural-based implementations such as multilayer perceptronstrained with backpropagation, or self-organizing maps. Suchimplementations provide an efficient generalization, i.e.,fast learning, and designate the critic, the reinforcementfunction definition, as the real issue. The paper discussesQ-learning for robots and Q-Kohon self organising map.
CITATION STYLE
Touzet, C. F., & Santos, J. M. (2001). Q-learning and robotics. In Simulation in Industry ’2001. 13th European Simulation Symposium 2001. ESS’2001. SCS Eur. BVBA, Ghent, Belgium (pp. 685–688).
Mendeley helps you to discover research relevant for your work.