Feature Selection for Neuro‐Dynamic Programming
Dayu Huang, W. Chen, Prashant G. Mehta, Sean Meyn, Amit Surana · 2012
Neuro-dynamic programming encompasses techniques from both reinforcement learning and approximate dynamic programming. Feature selection refers to the choice of basis that defines the function class that is required in the application of these techniques. This chapter reviews two popular approaches to neuro-dynamic programming, TD- and Q-Learning. It demonstrates how insight from idealized models can be used as a guide for feature selection for these algorithms. Several approaches are surveyed, including fluid and diffusion models, and the application of idealized models arising from mean-field game approximations. The theory is illustrated with several examples. One possible approach to parameterized reinforcement learning might emerge through the approximate LP approaches. Controlled Vocabulary Terms dynamic programming; non-Newtonian fluids