arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.04493cs.AI
收藏

动态重用人/Agent演示先验知识的交互式强化学习

Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human/Agent's Demonstration

Washington State University(华盛顿州立大学)

Zhaodong Wang, Matthew E. Taylor

摘要:

强化学习近年来取得了许多成功。然而,这些成功通常需要非常大量的数据之前,代理实现可接受的性能。本文介绍了一种新的方式,打击这种要求,利用现有的(人或代理)的知识。特别是,本文使用代理和人类的演示,允许未经训练的代理快速实现高性能。我们经验比较,并突出的弱点,HAT和CHAT,知识从源代理/人类转移到目标代理的方法。本文介绍了一种有效的迁移方法,DRoP,结合离线知识(学习前记录的演示)与在线基于信心的性能分析。DRoP动态地涉及演示者的知识,将其集成到强化学习代理的在线学习循环中,以实现高效和鲁棒的学习。

英文摘要:

Reinforcement learning has enjoyed multiple successes in recent years. However, these successes typically require very large amounts of data before an agent achieves acceptable performance. This paper introduces a novel way of combating such requirements by leveraging existing (human or agent) knowledge. In particular, this paper uses demonstrations from agents and humans, allowing an untrained agent to quickly achieve high performance. We empirically compare with, and highlight the weakness of, HAT and CHAT, methods of transferring knowledge from a source agent/human to a target agent. This paper introduces an effective transfer approach, DRoP, combining the offline knowledge (demonstrations recorded before learning) with online confidence-based performance analysis. DRoP dynamically involves the demonstrator's knowledge, integrating it into the reinforcement learning agent's online learning loop to achieve efficient and robust learning.

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。

↑