Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

Unbiased KL Estimate

An unbiased KL estimate obtained by correcting the K3 estimator with the importance-sampling ratio between current and old policies.

sources
2
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 3

Documented in

Evidence

3 spans quoted from the sources, strongest treatment first.

we correct the K3 estimator (Schulman, 2020) to obtain an unbiased KL estimate using the importance-sampling ratio between the current policy πθ and the old policy πold.

usedtraining objectivein DeepSeek-V3.2DeepSeek

we correct the K3 estimator (Schulman, 2020) to obtain an unbiased KL estimate using the importance-sampling ratio between the current policy πθ and the old policy πold.

usedoptimizationin DeepSeek-V3.2DeepSeek

we correct the K3 estimator (Schulman, 2020) to obtain an unbiased KL estimate using the importance-sampling ratio between the current policy and the old policy.

usedoptimizationin DeepSeek-V3.2DeepSeek

Filed alongside

Other methods under post-training :: reinforcement learning algorithm.