Variance reduction

In the previous chapter, I briefly mentioned that one of the ways to improve the stability of policy gradient methods is to reduce the variance of the gradient. Now let’s try to understand why this is important and what it means to reduce the variance. In statistics, variance is the expected square deviation of a random variable from the expected value of that variable:

Variance shows us how far values are dispersed from the mean. When variance is high, the random variable can take values that deviate widely from the mean. In the following plot, there is a normal (Gaussian) distribution with the same value for the mean, μ = 10, but with different values for the variance.

Figure 12.1: The effect of variance on Gaussian distribution

Now let’s return to policy gradients. It was stated in the previous chapter that the idea is to increase the probability of good actions and...