There is a typo of the off-policy actor-critic algorithm in chapter 10

[ichord]

At page 226, section 10.3.3

I think the π(at|st,θ) should be π(at|st,θt)

[MathFoundationRL]

You are right. They should be theta_t. Thanks for pointing out the typo.

[ichord]

Thanks so much for your work and opening the course. This book and the course are so great.