Since the optimal 
policy is the policy that maximizes the expected rewards, therefore,
,where 
means the expected value of the rewards obtained from the sequence of states agent observes if it follows the 
policy. Thus, 
outputs ...
The Bellman equations
,Get Reinforcement Learning with TensorFlow 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.
