We can apply the same to Sarsa, which uses a similar update rule, but we'll approximate the action-value function instead:
The same goes for Q-learning:
Value approximation for Sarsa and Q-learning
Get Python Deep Learning - Second Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
