arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.09725cs.AI
收藏

通过Attorney Utility Preservation的保守机构

Conservative Agency via Attainable Utility Preservation

Oregon State University(俄勒冈州立大学);UC Berkeley(加州大学伯克利分校)

Alexander Matt Turner, Dylan Hadfield-Menell, Prasad Tadepalli

摘要:

奖励函数很容易被错误指定;虽然设计者可以在观察到错误后进行纠正,但追求错误指定的奖励函数的智能体可以不可逆地改变其环境的状态。如果这种变化妨碍了正确指定的奖励函数的优化,那么纠正是徒劳的。例如,一个机器人工厂助理可能会因为奖励错误而损坏昂贵的设备;即使设计师立即纠正了奖励功能,损坏也已经造成。为了减轻这种风险,我们引入了一种方法,该方法平衡了主要奖励函数的优化与优化辅助奖励函数的能力的保留。令人惊讶的是,即使辅助奖励函数是随机生成的,因此无法提供关于正确指定的奖励函数的信息,这种方法也会导致保守有效的行为。

英文摘要:

Reward functions are easy to misspecify; although designers can make corrections after observing mistakes, an agent pursuing a misspecified reward function can irreversibly change the state of its environment. If that change precludes optimization of the correctly specified reward function, then correction is futile. For example, a robotic factory assistant could break expensive equipment due to a reward misspecification; even if the designers immediately correct the reward function, the damage is done. To mitigate this risk, we introduce an approach that balances optimization of the primary reward function with preservation of the ability to optimize auxiliary reward functions. Surprisingly, even when the auxiliary reward functions are randomly generated and therefore uninformative about the correctly specified reward function, this approach induces conservative, effective behavior.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑