Abstract
This paper proposes an incremental learning approach to control autonomous robots based on local networks. This approach integrates different learning techniques in a conceptually simple architecture. The robot does not learn from scratch, but uses two types of bias: builtin reflexes (domain knowledge) and advice. The robot adds a new unit to the neural network whenever it uses the reflexes or receives an advice. This unit is integrated into a topology preserving map and associates a region around the current situation to either the computed reflex or the advice. The resulting reaction rule is then tuned by means of reinforcement learning and self-organizing rules. Experimental results show that the robot TESEO rapidly learns suitable behavioral strategies.
Preview
Unable to display preview. Download preview PDF.
References
Barto, A., Sutton, R., & Anderson, C. (1983). IEEE Trans. SMC, 13:835–846.
Clouse, J.A. & Utgoff, P.E. (1992). 9th Int. Conf. on Machine Learning.
Dayan, P. & Sejnowski, T.J. (1994). Machine Learning, 14:295–301.
Fritzke, B. (1995). Advances in Neural Information Processing Systems 7.
Gordon, G.J. (1995). 12th Int. Conf. on Machine Learning.
Maclin, R. & Shavlik, J.W. (1996). Machine Learning, 22:251–281.
McCallum, R.A. (1996). IEEE Trans. SMC—Part B, 26:464–473.
Millán, J. del R. (1996). IEEE Trans. SMC—Part B, 26:408–420.
Millán, J. del R. & Heikkonen, J. (1996). Working paper, March.
Singh, S.P. & Sutton, R.S. (1996). Machine Learning, 22:123–158.
Sutton, R.S. (1988). Machine Learning, 3:9–44.
Sutton, R.S. (1996). Advances in Neural Information Processing Systems 8.
Tsitsiklis, J.N. & Van Roy, B. (1996). Machine Learning, 22:59–94.
Varsta, M., Heikkonen, J., & Millán, J. (1997). Workshop on Self-Organizing Maps.
Watkins, C.J.C.H. (1989). Ph.D. Thesis, Cambridge University, England.
Williams, R.J. (1992). Machine Learning, 8:229–256.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
del R. Millân, J. (1997). Incremental acquisition of local networks for the control of autonomous robots. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020242
Download citation
DOI: https://doi.org/10.1007/BFb0020242
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive