Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

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

Abstract : 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Cédric Colas Connect in order to contact the contributor
Submitted on : Wednesday, January 6, 2021 - 1:11:45 PM
Last modification on : Friday, January 21, 2022 - 3:22:21 AM
Long-term archiving on: : Wednesday, April 7, 2021 - 7:57:29 PM


Files produced by the author(s)


  • HAL Id : hal-03099887, version 1


Cédric Colas, Ahmed Akakzia, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud. Language-Conditioned Goal Generation: a New Approach to Language Grounding in RL. 2021. ⟨hal-03099887⟩



Les métriques sont temporairement indisponibles