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

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?]