Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL

Understand

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.