Abstract / Description of output
The least squares approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. In this paper, we propose a new basis function based on geodesic Gaussian kernels, which exploits the non-linear manifold structure induced by the Markov decision processes. The usefulness of the proposed method is successfully demonstrated in a simulated robot arm control and Khepera robot navigation.
Original language | English |
---|---|
Title of host publication | Robotics and Automation, 2007 IEEE International Conference on |
Pages | 1733-1740 |
Number of pages | 8 |
ISBN (Electronic) | 1-4244-0602-1 |
DOIs | |
Publication status | Published - 2007 |