Question: 8. In SARSA with linear function approximation, using linear regression to minimize r + Qw(s, a) Qw(s, a), gives a different algorithm than Figure
8. In SARSA with linear function approximation, using linear regression to minimize r + γQw¯¯¯(s′, a′) − Qw¯¯¯(s, a), gives a different algorithm than Figure 12.7. Explain what you get and why what is described in the text may be preferable (or not).
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
