← All symbols

Symbol in context

DKLD_{\mathrm{KL}}

This entry links every published equation using this exact notation. Its meaning may change between equations.

Used in 4 equations

max⁡θ  Ex, y∼πθ[rϕ(x,y)]  −  β DKL(πθ ∥ πref).\max_\theta \; \mathbb{E}_{x,\, y\sim\pi_\theta}\big[r_\phi(x,y)\big] \;-\; \beta \, D_{\mathrm{KL}}\big(\pi_\theta \,\Vert\, \pi_{\mathrm{ref}}\big).

The Main Technical Approaches to AI Alignment, Compared · Equation 2

This mathematical expression combines the displayed quantities; its precise role follows from the surrounding article text.

Equation guide → · This term → · Article →
J(θ)=Ex∼D, y∼πθ(⋅∣x)[r(x,y)]−βDKL(πθ(⋅∣x) ∥ πref(⋅∣x))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)

Claude, From First Principles: Training, Constitutional Methods, and What Actually Shapes a Response · Equation 6

This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.

Equation guide → · This term → · Article →
E[rθ(x,y)]−β E[DKL ⁣(πRL ∥ πSFT)]+γ E[log⁡πRL(x)],\mathbb{E}\big[r_\theta(x,y)\big] - \beta\,\mathbb{E}\big[D_{\mathrm{KL}}\!\left(\pi^{\mathrm{RL}} \,\|\, \pi^{\mathrm{SFT}}\right)\big] + \gamma\,\mathbb{E}\big[\log \pi^{\mathrm{RL}}(x)\big],

What RLHF Actually Optimises: Rated Agreeableness, and Where It Parts from Helpfulness · Equation 3

This mathematical expression combines the displayed quantities; its precise role follows from the surrounding article text.

Equation guide → · This term → · Article →