Objective Robustness in Deep Reinforcement Learning
Objective Robustness in Deep Reinforcement Learning
复制标题
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Jack Koch;L. Langosco;J. Pfau;James Le;Lee D. Sharkey
中科院分区：
文献类型：
--
作者：
Jack Koch;L. Langosco;J. Pfau;James Le;Lee D. Sharkey
本文研究了强化学习(RL)中的客观健壮性失效，这是一种分布外的健壮性失效。目标稳健性失败发生在RL代理在分布之外保留其能力但追求错误目标时。这种失败带来的风险与文献中通常认为的健壮性问题不同，因为它涉及到利用自己的能力追求错误目标的代理，而不仅仅是没有做任何有用的事情。我们给出了客观稳健性失效的fi第一个显式的经验证明，并给出了其原因的部分刻画。
We study objective robustness failures, a type of out-of-distribution robustness failure in reinforcement learning (RL). Objective robustness failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong objective. This kind of failure presents different risks than the robustness problems usually considered in the literature, since it involves agents that leverage their capabilities to pursue the wrong objective rather than simply failing to do anything useful. We provide the first explicit empirical demonstrations of objective robustness failures and present a partial characterization of its causes.