Continual Robot Learning with Constructive Neural Networks
In this paper, we present an approach for combining reinforcement learning, learning by imitation, and incremental hierarchical development. We apply this approach to a realistic simulated mobile robot that learns to perform a navigation task by imitating the movements of a teacher and then continues to learn by receiving reinforcement. The behaviours of the robot are represented as sensation-action rules in a constructive high-order neural network. Preliminary experiments are reported which show that incremental, hierarchical development, bootstrapped by imitative learning, allows the robot to adapt to changes in its environment during its entire lifetime very efficiently, even if only delayed reinforcements are given.
Unable to display preview. Download preview PDF.
- Paul Bakker and Yasuo Kuniyoshi. Robot see, robot do: An overview of robot imitation. In Proceedings of the AISB’96 Workshop on Learning in Robots and Animals, Brighton, UK, 1996.Google Scholar
- John Demiris and Gillian Hayes. Imitative learning mechanisms in robots and humans. In Volker Klingspor, editor, Proceedings of the Fifth European Workshop on Learning Robots, Bari, Italy, 1996.Google Scholar
- Marco Dorigo and Marco Colombetti. The role of the trainer in reinforcement learning. In S. Mahadevan et al., editors, Proceedings of the Workshop on Robot Learning held as part of the 1994 International Conference on Machine Learning (ML’94) and the 1994 ACM Conference on Computational Learning Theory (COLT’4), pages 37–45, 1994.Google Scholar
- Gillian Hayes and John Demiris. A robot controller using learning by imitation. In Proceedings of the Second International Symposium on Intelligent Robotic Systems, Grenoble, France, 1994.Google Scholar
- Leslie Pack Kaelbling, Michael L. Littman, and Andrew W. Moore. Reinforcement learning: A survey. Artificial Intelligence Research, 4:237–285, 1996.Google Scholar
- Yasuo Kuniyoshi, Masayuki Inaba, and Hirochika Inoue. Learning by watching: Extracting reusable task knowledge from visual observation of human performance. IEEE Transactions on Robotics and Automation, 10(6), 1994.Google Scholar
- R. L. Riolo. The emergence of default hierarchies in learning classifier systems. In J. D. Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms, pages 322–327. Morgan Kaufmann, 1989.Google Scholar