Unverified50% confidenceFactExact time
SAC的自动调节机制中,目标熵通常设为-dim(A),即动作空间维度的负值
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
SAC训练崩溃之谜:策略熵坍塌与DIAYN调试指南
Related Entities
Cite This Claim
Stable URI
https://kongchang.com/claim/982252API
curl https://kongchang.com/api/v1/knowledge/claims/982252MCP
get_claim(id=982252)