Unverified50% confidenceFactExact time
In on-policy distillation, the student model first generates trajectories itself, and then the teacher model provides supervision signals for these paths, thereby avoiding the distribution shift between offline data and student behavior.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThis experiment adopts trajectory-level distillation, which belongs to the category of behavioral cloning, directly having the student model imitate the external behavioral sequences of the teacher model.79% similarUnverifiedOn-policy distillation (OPD) has the student model generate its own trajectories, and then the teacher model provides supervision signals on those trajectories.78% similarVerifiedModel Distillation in machine learning refers to training a small student model using the outputs of a large teacher model, in order to compress model size while retaining capability.76% similarUnverifiedPolicy distillation typically refers to using a student policy to imitate the behavior of one or more teacher policies.74% similarVerifiedIn offline distillation, training data is generated once by the teacher model and fixed, with the student model learning from a static dataset.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013301API
curl https://kongchang.com/api/v1/knowledge/claims/1013301MCP
get_claim(id=1013301)