arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.04201cs.AIcs.LG
收藏

具有不确定人类反馈的学习行为

Learning Behaviors with Uncertain Human Feedback

Nanyang Technological University(南洋理工大学);Dartmouth College(达特茅斯学院)

Xu He, Haipeng Chen, Bo An

摘要:

人工反馈被广泛用于训练智能体。然而,以前的作品很少考虑人类提供反馈时的不确定性,特别是在最佳行动对训练者来说并不明显的情况下。例如,次优行为的奖励可以是随机的,有时会超过最优行为的奖励,这在游戏或现实世界中很常见。培训师可能会对次优行动提供正反馈,对最优行动提供负反馈,甚至在某些混乱的情况下不提供反馈。现有的作品,利用期望最大化(EM)算法和治疗的反馈模型作为隐藏参数,不考虑学习环境和人类反馈的不确定性。为了解决这一挑战,我们引入了一个新的反馈模型,考虑了人类反馈的不确定性。然而,这在EM算法中引起棘手的演算。为此,我们提出了一种新的近似EM算法,其中我们近似的期望步骤与梯度下降方法。实验结果表明,在两个合成场景和两个现实世界的情况下,人类参与者的优越性能,我们所提出的方法。

英文摘要:

Human feedback is widely used to train agents in many domains. However, previous works rarely consider the uncertainty when humans provide feedback, especially in cases that the optimal actions are not obvious to the trainers. For example, the reward of a sub-optimal action can be stochastic and sometimes exceeds that of the optimal action, which is common in games or real-world. Trainers are likely to provide positive feedback to sub-optimal actions, negative feedback to the optimal actions and even do not provide feedback in some confusing situations. Existing works, which utilize the Expectation Maximization (EM) algorithm and treat the feedback model as hidden parameters, do not consider uncertainties in the learning environment and human feedback. To address this challenge, we introduce a novel feedback model that considers the uncertainty of human feedback. However, this incurs intractable calculus in the EM algorithm. To this end, we propose a novel approximate EM algorithm, in which we approximate the expectation step with the Gradient Descent method. Experimental results in both synthetic scenarios and two real-world scenarios with human participants demonstrate the superior performance of our proposed approach.

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。

↑