In SARSA with linear function approximation, using linear regression to minimize r + Qw(s , a )

Question:

In SARSA with linear function approximation, using linear regression to minimize r + γQw(s

, a

) − Qw(s,

a) gives a different algorithm than Figure 13.8 (page 602). Explain what you get and why what is described in the text may be preferable (or not). [Hint: what should the weights be adjusted to better estimate?]

Fantastic news! We've Found the answer you've been seeking!

Step by Step Answer:

Related Book For  book-img-for-question
Question Posted: