How to incorporate function approximation algorithm into q-learning algorithm?
Answers
Answered by
0
In reinforcement learning, linear function approximation is often used when large state spaces are present. (When look up tables become unfeasible.)
The form of the Q−Q−value with linear function approximation is given by
Q(s,a)=w1f1(s,a)+w2f2(s,a)+⋯,Q(s,a)=w1f1(s,a)+w2f2(s,a)+⋯,
where wiwi are the weights, and fifi are the features.
The features are predefined by the user. My question is, how are the weights assigned?
I have read/downloaded some lecture slides on Q−Q−learning with function approximation. Most of them have slides on linear regression that follow. Since they are just slides, they tend to be incomplete. I wonder what the connection/relation is between the two topics.
The form of the Q−Q−value with linear function approximation is given by
Q(s,a)=w1f1(s,a)+w2f2(s,a)+⋯,Q(s,a)=w1f1(s,a)+w2f2(s,a)+⋯,
where wiwi are the weights, and fifi are the features.
The features are predefined by the user. My question is, how are the weights assigned?
I have read/downloaded some lecture slides on Q−Q−learning with function approximation. Most of them have slides on linear regression that follow. Since they are just slides, they tend to be incomplete. I wonder what the connection/relation is between the two topics.
Similar questions