340 search results - page 2 / 68 » Kernelized value function approximation for reinforcement le... |
ICCBR
2005
Springer
13 years 11 months ago
2005
Springer
CBR is one of the techniques that can be applied to the task of approximating a function over high-dimensional, continuous spaces. In Reinforcement Learning systems a learning agen...
AAAI
2011
12 years 5 months ago
2011
We describe the Fourier Basis, a linear value function approximation scheme based on the Fourier Series. We empirically evaluate its properties, and demonstrate that it performs w...
NIPS
1994
13 years 6 months ago
1994
To appear in: G. Tesauro, D. S. Touretzky and T. K. Leen, eds., Advances in Neural Information Processing Systems 7, MIT Press, Cambridge MA, 1995. A straightforward approach to t...
AMAI
2004
Springer
13 years 10 months ago
2004
Springer
ICRA
2009
IEEE
14 years 2 days ago
2009
IEEE
Abstract— Least-squares policy iteration is a useful reinforcement learning method in robotics due to its computational efficiency. However, it tends to be sensitive to outliers...