从活动描述中进行交互式学习
Interactive Learning from Activity Description
摘要：
我们提出了一种新的交互式学习协议，使培训请求履行代理口头描述他们的活动。与模仿学习（IL）不同，我们的协议允许教学代理以最适合他们的语言提供反馈。与强化学习（RL）中的奖励相比，描述反馈更丰富，并允许提高样本复杂度。我们开发了一个概率框架和一个算法，实际上实现了我们的协议。两个具有挑战性的请求满足问题的实证结果表明，我们的方法的优势：与RL基线相比，它是更有效的样本;与IL基线相比，它实现了有竞争力的成功率，而不需要教学代理能够证明所需的行为使用学习代理的行动。除了经验评估，我们还提供了理论保证，我们的算法在一定的假设下的教师和环境。
英文摘要：
We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Unlike imitation learning (IL), our protocol allows the teaching agent to provide feedback in a language that is most appropriate for them. Compared with reward in reinforcement learning (RL), the description feedback is richer and allows for improved sample complexity. We develop a probabilistic framework and an algorithm that practically implements our protocol. Empirical results in two challenging request-fulfilling problems demonstrate the strengths of our approach: compared with RL baselines, it is more sample-efficient; compared with IL baselines, it achieves competitive success rates without requiring the teaching agent to be able to demonstrate the desired behavior using the learning agent's actions. Apart from empirical evaluation, we also provide theoretical guarantees for our algorithm under certain assumptions about the teacher and the environment.
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。
