specific method · filed under post-training
Derived-Latency Penalty
A reward penalty based on execution latency estimated from a dependency DAG's critical path.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
Derived latency is computed by representing execution events and their collaboration dependencies as a directed acyclic graph (DAG), assigning costs from token counts at fixed prefill/decode rates plus measured tool-execution time, and taking the length of the critical path.
usedtraining objectivein DeepSeek-V4.1-FlashDeepSeek
Filed alongside
Other methods under post-training :: reinforcement learning algorithm.
Group Relative Policy OptimizationReinforcement LearningGroupwise Advantage RedistributionFreezing the MoE Router During Reinforcement LearningIcePopOff-Policy Sequence MaskingReinforcement Learning from Verifiable RewardsRollout Routing ReplayUnbiased KL EstimateAsynchronous Group Relative Policy OptimizationChain-of-Thought Reinforcement LearningDirect Double-Sided Importance SamplingKeep Sampling MaskMixed Reinforcement LearningPivot Reinforcement LearningReinforcement Learning Post-TrainingAbstention TrainingAdvantage ShapingAgentic RL Task MixCISPO with Length-Weighted Leave-One-Out Group-Relative AdvantagesConcatenated Routing ReplayDomain-Specialized RL ExpertsDomain-Specific GRPO TrainingDropping All-Zero-Advantage Groups