Reading Group in Reinforcement Learning

Nov 9: Least-Squares Policy Iteration, Michail G. Lagoudakis, Ronald Parr; 4(Dec):1107-1149, 2003.
Oct 19: Amari and Douglas, Why Natural Gradient?, Acoustics, Speech, and Signal Processing, 1998. ICASSP '98, and S. Kakade, A Natural Policy Gradient, NIPS 2001.
Oct 12: Natural Gradient Works Efficiently in Learning, by Shun-Ichi Amari, Neural Computation, 1998.
Oct 5: Jan Peters, Sethu Vijayakumar, and Stefan Schaal, Reinforcement Learning for Humanoid Robots - policy gradients and beyond, Third IEEE International Conference on Humanoid Robotics 2003, Germany.
Sept 28: Policy Gradient Methods for Reinforcement Learning with Function Approximation, by Sutton et al.
August 18th: Another paper by Smart, Practical Reinforcement Learning in Continuous Spaces, Proceedings of the Sixteenth International Conference on Machine Learning, 2000.
August 11th: The paper by Smart is short and easy to read. Chapter 8 of the book is much longer; we won't get through all of it.
- Explicit Manifold Representations for Value-Function Approximation in Reinforcement Learning, by William Smart, Eighth International Symposium on Artificial Intelligence and Mathematics, January, 2004, and
- Chapter 8 Generalization and Function Approximation, from Reinforcement Learning: An Introduction Richard S. Sutton and Andrew G. Barto.
August 4th:
- Reinforcement Learning in Continuous Time and Space, by Kenji Doya.

The following papers and topics have been suggested for future discussions.

Least-Squares Temporal Difference Learning, Boyan, ICML99.
Actor-Critic Algorithms, V. R. Konda and J. N. Tsitsiklis, SIAM Journal on Control and Optimization, Vol. 42, No. 4, 2003, pp. 1143-1166. and its Appendix
On-line EM Reinforcement Learning, by Yoshimoto, Ishii and Sato, IJCNN2000).

Reinforcement Learning: An Introduction, by Richard S. Sutton and Andrew G. Barto, MIT Press, Cambridge, MA, 1998.
Neuro-Dynamic Programming, by Dimitri P. Bertsekas and John Tsitsiklis.