Unverified50% confidenceFactExact time
Self-Distillation Policy Optimization (SDPO) provides dense token-level supervision signals to the student model through a feedback-conditioned "self-teacher".
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedOnline policy distillation (OPD) has the student model generate its own training responses, which are then supervised by the teacher model.75% similarUnverifiedThe key mechanism of RM-OPD is applying token-level dense supervision on critiques generated by the student itself, making the supervision distribution consistent with the student's current policy distribution and alleviating the training-inference distribution mismatch problem.72% similarUnverifiedOn-policy distillation requires the student to first generate its own prefix trajectory, after which the teacher provides guidance at the states the student actually reaches, so the state distributions are aligned, and it is usually more stable on long-horizon tasks where errors tend to accumulate.72% similarUnverifiedFor correct rollouts, APSD adopts an interpolation strategy, with the target distribution lying between the student and the self-teacher, preserving the student's already-successful generation behaviors.71% similarUnverified教师-学生蒸馏框架先训练可访问完整环境信息的教师策略，再蒸馏到仅依赖机载传感器的学生策略中以实现真实硬件部署69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074082API
curl https://kongchang.com/api/v1/knowledge/claims/1074082MCP
get_claim(id=1074082)