Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Target tracking control of a mobile robot using a brain limbic system based control strategy
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Hi-index | 0.00 |
A solution to the problem of model-free intelligent attitude control of aerospace launch vehicles is presented. Emphasis is placed on the development of learning the proper action through reinforcement learning for problems that have no model or in which the model is too complex. One approach to solving this class of problems is via motivation from emotional learning mechanism in the mammalian brain. A simple but effective mathematical model from the emotional learning mechanism in the human brain is presented and developed to solve the closed-loop command tracking problem. The emotional learning mechanism needs a set of sensory inputs and a reinforcing signal to produce action. Determination and tuning of the parameters of the reinforcing signal and sensory input are left to be solved through evolution by a genetic algorithm. It is shown in simulations that the mathematical model of the emotional learning mechanism can be initialized as a powerful feedback control algorithm.