[KongchangAI]
Unverified50% confidenceFactExact time

Score Centering places the effect of the baseline on the off-policy-corrected score term, rather than treating only the reward side.

1
Sources
50%
Confidence
Long-term
Relevance
9/20/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/937383
API
curl https://kongchang.com/api/v1/knowledge/claims/937383
MCP
get_claim(id=937383)