Combining the Best of the Two Worlds: Inheritance Versus Experience
In this paper a hybrid approach to the autonomous navigation of robots in cluttered environment with unknown obstacles is introduced. It is shown the efficiency of the hybrid solution by combining the optimization power of evolutionary algorithms and at the same time the efficiency of the Reinforcement Learning in real-time and on-line situations. Experimental results concerning the navigation of a L-shaped robot in a cluttered environment with unknown obstacles in which appear real-time and on-line constraints well-suited to RL algorithms and extremely high dimension of the state space usually unpractical for RL algorithms but at the same time well-suited to evolutionary algorithms, are also presented. The experimental results confirm the validity of the hybrid approach to solve hard real-time, on-line and high dimensional robot motion control problems.
KeywordsEvolutionary Algorithm Reinforcement Learn Markov Decision Process Control Rule Goal Position
Unable to display preview. Download preview PDF.
- 1.Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
- 2.Wang, P.P.: Computing with Words. Wiley Interscience, New York (2001)Google Scholar
- 3.Watkins, C.J.: Models of Delayed Reinforcement Learning. PhD Thesis Dissertation, Psychology Department, Cambridge University, Cambridge, UK (1989)Google Scholar
- 7.Holland, J.H.: Escaping brittleness: The possibilities of general purpose learning algorithms applied in parallel rule-based systems. In: Michaiski, R.S., Carbonell, J.G., Mitchell, T.M. (eds.) Machine Learning II, pp. 593–623 (1986)Google Scholar