specific method · filed under post-training
Mixed Reinforcement Learning
A single RL stage that combines reasoning, agent, and human-alignment training.
Also called Mixed RL Training.
- sources
- 2
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
we merge reasoning, agent, and human alignment training into one RL stage.
corepost trainingin DeepSeek-V3.2DeepSeek
As DeepSeek-V3.2-Exp, we merge reasoning, agent, and human alignment training into one RL stage.
corepost trainingin DeepSeek-V3.2DeepSeek
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 MaskPivot Reinforcement LearningReinforcement Learning Post-TrainingAbstention TrainingAdvantage ShapingAgentic RL Task MixCISPO with Length-Weighted Leave-One-Out Group-Relative AdvantagesConcatenated Routing ReplayDerived-Latency PenaltyDomain-Specialized RL ExpertsDomain-Specific GRPO TrainingDropping All-Zero-Advantage Groups