论文标题
通过演示推理的加强学习
Reinforcement Learning via Reasoning from Demonstration
论文作者
论文摘要
示范是人类为加强学习者提供援助的一种吸引人的方式。该领域中的大多数方法主要视为行为偏见的来源。但是，在稀疏的奖励任务中，人类似乎将示威视为因果知识的来源。本文提出了一个以这种人为灵感的方式从演示中受益的代理商的框架。在此框架中，代理商通过观察来开发因果模型，以及从这些知识到分解任务以进行有效强化学习的原因。实验结果表明，在一系列稀疏的奖励任务中，演示（RFD）的基本推理的基本实施是有效的。
Demonstration is an appealing way for humans to provide assistance to reinforcement-learning agents. Most approaches in this area view demonstrations primarily as sources of behavioral bias. But in sparse-reward tasks, humans seem to treat demonstrations more as sources of causal knowledge. This paper proposes a framework for agents that benefit from demonstration in this human-inspired way. In this framework, agents develop causal models through observation, and reason from this knowledge to decompose tasks for effective reinforcement learning. Experimental results show that a basic implementation of Reasoning from Demonstration (RfD) is effective in a range of sparse-reward tasks.
