Unverified50% confidenceFactExact time
若自动温度调节的目标熵设置不当,α可能被优化到过小的值导致探索动机消失,策略坍缩到确定性输出
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/982251API
curl https://kongchang.com/api/v1/knowledge/claims/982251MCP
get_claim(id=982251)