[KongchangAI]
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/982251
API
curl https://kongchang.com/api/v1/knowledge/claims/982251
MCP
get_claim(id=982251)