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.
翻译:人类的反馈被广泛用于在许多领域培训代理人。然而,以前的工作很少考虑当人类提供反馈时的不确定性,特别是当最佳行动对培训员来说并不明显时。例如,亚最佳行动的奖励可能是随机的,有时会超过最佳行动的奖励,这在游戏或现实世界中是常见的。培训者可能会为次优的行动提供积极的反馈,对最佳行动的消极反馈,甚至在某些混乱的情况下甚至不会提供反馈。利用现有的工作,利用期望最大化算法,将反馈模型作为隐性参数处理,不考虑学习环境和人类反馈中的不确定性。为了应对这一挑战,我们引入了一个新的反馈模型,考虑人类反馈的不确定性。然而,这在EM算法中造成了难以控制的微积分。为此,我们提出了一种新颖的EM算法,其中我们将期望与梯族法相近。在合成情景和两种真实世界情景中与人类参与者的实验结果显示了我们拟议方法的优异性表现。