arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.05862cs.LG
收藏

了解学习奖励函数

Understanding Learned Reward Functions

UC Berkeley(加州大学伯克利分校)

Eric J. Michaud, Adam Gleave, Stuart Russell

摘要:

在许多现实世界的任务中,不可能在程序上指定RL代理的奖励函数。在这种情况下,奖励功能必须从与人类的互动和观察中学习。然而,用于奖励学习的当前技术可能无法产生准确反映用户偏好的奖励函数。在奖励学习方面缺乏重大进展的情况下,能够审计学习的奖励函数以验证它们是否真正捕获用户偏好是很重要的。在本文中,我们研究的技术解释学习奖励功能。特别是,我们应用显着性方法来识别故障模式和预测的回报函数的鲁棒性。我们发现,学习奖励功能往往实现令人惊讶的算法,依赖于偶然的方面的环境。我们还发现,现有的可解释性技术往往参加奖励输出的不相关的变化,这表明奖励可解释性可能需要显着不同的方法从政策的可解释性。

英文摘要:

In many real-world tasks, it is not possible to procedurally specify an RL agent's reward function. In such cases, a reward function must instead be learned from interacting with and observing humans. However, current techniques for reward learning may fail to produce reward functions which accurately reflect user preferences. Absent significant advances in reward learning, it is thus important to be able to audit learned reward functions to verify whether they truly capture user preferences. In this paper, we investigate techniques for interpreting learned reward functions. In particular, we apply saliency methods to identify failure modes and predict the robustness of reward functions. We find that learned reward functions often implement surprising algorithms that rely on contingent aspects of the environment. We also discover that existing interpretability techniques often attend to irrelevant changes in reward output, suggesting that reward interpretability may need significantly different methods from policy interpretability.

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。

↑