How to formulate problem with State is a combination of multiple factors?

ShangtongZhang / reinforcement-learning-an-introduction

Python Implementation of Reinforcement Learning: An Introduction

MIT License

13.45k stars 4.81k forks source link

How to formulate problem with State is a combination of multiple factors? #114

Closed MJeremy2017 closed 5 years ago

MJeremy2017 commented 5 years ago

Hi, shangtong I am reading the book and following your implementation code. In chapter 9, the random walk example, the book mentioned V(s, w) = W*S, where in random walk the state is 1 dimension, in its simplest form it could be like V(s, w) = w_1*s + w_0, but I wonder what if the state has 2 or more components? say, S = S(position, time), how to rewrite the above function? Is it V(s, w) = w_1*(position + time) + w_0?

ShangtongZhang commented 5 years ago

function approximation with features, e.g., tile coding