论文标题
语言条件的目标生成：RL语言基础的新方法
Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL
论文作者
论文摘要
在现实世界中，语言代理人也是体现的代理人：它们在物理世界中感知并起作用。语言基础的概念质疑语言与实施方案之间的相互作用：学习代理如何将语言代表与物理世界联系起来？加强学习社区最近在指导辅助代理的框架下解决了这个问题。在这些代理商中，行为政策或奖励功能以自然语言表达的指令的嵌入为条件。本文提出了另一种方法：使用语言来调节目标生成器。鉴于任何目标条件政策，可以训练一个具有语言条件的目标生成器，以为代理人生成语言不可能的目标。这种方法允许从语言获取中解除感觉运动学习，并使代理商能够为任何给定的教学展示各种行为。我们提出了这种方法的特殊实例化，并证明了它的好处。
In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world. The notion of Language Grounding questions the interactions between language and embodiment: how do learning agents connect or ground linguistic representations to the physical world ? This question has recently been approached by the Reinforcement Learning community under the framework of instruction-following agents. In these agents, behavioral policies or reward functions are conditioned on the embedding of an instruction expressed in natural language. This paper proposes another approach: using language to condition goal generators. Given any goal-conditioned policy, one could train a language-conditioned goal generator to generate language-agnostic goals for the agent. This method allows to decouple sensorimotor learning from language acquisition and enable agents to demonstrate a diversity of behaviors for any given instruction. We propose a particular instantiation of this approach and demonstrate its benefits.
