Unverified50% confidenceFactExact time
TRPO由John Schulman等人在2015年提出，使用信任域方法约束新旧策略间的KL散度
1
Sources
50%
Confidence
Long-term
Relevance
8/5/2026
First Seen
Sources
Related Claims
Cite This Claim
Stable URI
https://kongchang.com/claim/690914API
curl https://kongchang.com/api/v1/knowledge/claims/690914MCP
get_claim(id=690914)