#failure-mode

1 stories · 0 in 7 days · 0 in 30 days

Stories, products and papers tagged "failure-mode", newest first.

May 11

PapersOfficial00:17

Chinese content野外奖励函数缺陷：强化学习反直觉失败

理解奖励函数漏洞是构建鲁棒RL系统的核心挑战，直接影响实际部署的安全性与可靠性。

#reinforcement-learning #reward-function #robustness #failure-mode

Primary sourceOpenAI BlogSource

failure-mode · AI news | AITOP