Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Neuro-Dynamic Programming
Learning Options in Reinforcement Learning
Proceedings of the 5th International Symposium on Abstraction, Reformulation and Approximation
Least-squares policy iteration
The Journal of Machine Learning Research
The Linear Programming Approach to Approximate Dynamic Programming
Operations Research
Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)
Efficient solution algorithms for factored MDPs
Journal of Artificial Intelligence Research
Robust Approximate Bilinear Programming for Value Function Approximation
The Journal of Machine Learning Research
Approximate Dynamic Programming via a Smoothed Linear Program
Operations Research
Approximate Linear Programming for Average Cost MDPs
Mathematics of Operations Research
Hi-index | 0.00 |
Approximate Linear Programming (ALP) is a reinforcement learning technique with nice theoretical properties, but it often performs poorly in practice. We identify some reasons for the poor quality of ALP solutions in problems where the approximation induces virtual loops. We then introduce two methods for improving solution quality. One method rolls out selected constraints of the ALP, guided by the dual information. The second method is a relaxation of the ALP, based on external penalty methods. The latter method is applicable in domains in which rolling out constraints is impractical. Both approaches show promising empirical results for simple benchmark problems as well as for a realistic blood inventory management problem.