Symbol D_KL

The passage around this formula

The optimisation itself has a specific and revealing shape. Rather than maximising the fitted reward outright, the standard formulation constrains the updated policy to stay close to a reference policy, ordinarily the model just after supervised fine-tuning, one step removed from the raw pretrained prior: $J(\theta) = \mathbb{E}_{x \sim \mathcal{D},\ y \sim \pi_\theta(\cdot \mid x)}\left[r(x,y)\right] - \beta D_{\mathrm{KL}}\left(\pi_\theta(\cdot \mid x) \,\|\, \pi_{\mathrm{ref}}(\cdot \mid x)\right)$. The reward term r(x,y) pulls the policy toward whatever the fitted preference model scores highly; the Kullback–Leibler penalty, weighted by $\beta$ , pulls it back toward the reference distribution. That second term is not a minor regulariser. It is the load-bearing assumption behind the entire method: remove it, and a policy optimised hard enough against an imperfect…

Read this part in the article →