Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

Off-Policy Sequence Masking

Masking negative sequences that exhibit significant policy divergence, measured by KL divergence from the current policy.

Also called Off-policy sequence masking for GRPO.

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 mask negative sequences that introduce significant policy divergence, as measured by the KL divergence between the data-sampling policy πold and the current policy πθ.

usedtraining objectivein DeepSeek-V3.2DeepSeek

Off-Policy Sequence Masking To improve the efficiency of RL systems, we typically generate a large batch of rollout data, which is subsequently split into multiple mini-batches for several gradient update steps.

usedoptimizationin DeepSeek-V3.2DeepSeek

we mask negative sequences that introduce significant policy divergence, as measured by the KL divergence between the data-sampling policy and the current policy.

usedoptimizationin DeepSeek-V3.2DeepSeek

Filed alongside

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