Since I am relatively new to the field of reinforcement learning and I read through the classic book Reinforcement Learning: An Introduction by Sutton et. al., in Chapter 9 the authors mention several methods for feature construction, i.e. polynomial basis, Fourier basis functions, tile coding, etc.

My question is: are there good code bases or papers that apply these abstract principles to real problems, meaning games or robotic tasks? It would be great to get a better sense of how to construct features for one's own projects and it seems like a great learning experience to see illustrations of successful feature constructions.

Thanks in advance.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.