Instance-based reinforcement learning for robot path finding in continuous space
- 22 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (1062922X), 1229-1234
- https://doi.org/10.1109/icsmc.1997.638118
Abstract
This paper presents two methods of shaping autonomous mobile robots within a framework of instance-based reinforcement learning. The first one is instance-based classifier generator, which is used to learn primitive behaviors. The second one is reinforcement learning based on behavior sequence memory, which is used to learn optimal path and to distinguish hidden states. Learning capability of the proposed methods is confirmed through a path-finding task of a mobile robot in continuous space. Simulation results demonstrate that the robot can acquire behaviors such as light-seeking, collision-avoidance and wall-following, and it can also find the optimal paths in the alternately changing environments.Keywords
This publication has 3 references indexed in Scilit:
- Hidden state and reinforcement learning with instance-based state identificationIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1996
- Reinforcement Learning: A SurveyJournal of Artificial Intelligence Research, 1996
- Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic ProgrammingPublished by Elsevier ,1990