For questions related to the REINFORCE algorithm (or update rule), which is a policy gradient algorithm, that is, an algorithm which estimates the policy directly (that is, without first estimating any value function).

REINFORCE was introduced in 1988 and 1992 by Ronald J. Williams, respectively, in the papers "Toward a theory of reinforcement-learning connectionist systems" and "Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning".