Bellman's Optimality Equation

In this article, we will be walking through the concept behind Bellman's Optimality equation, and how it is used in the case of Reinforcement Learning.

V( s ) = a max ( R(s,a) )+γV(s'))−−> Bellman's equation for deterministic environment

Bellman’s optimality equation:

V * (s)= ∑ a π(a|s) . ∑ s' P(s'|a)[ E(r|s,as')+γ V * (s') ]

Bellman’s equation is one amongst other very important eq...