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

arXiv: https://arxiv.org/abs/2006.07043 · HTML: https://mlsanity.com/paper/2006.07043/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [Open-Ended Learning Leads to Generally Capable Agents](https://mlsanity.com/paper/2107.12808/) (2021)
- [Improving Intrinsic Exploration with Language Abstractions](https://mlsanity.com/paper/2202.08938/) (2022)
- [Intelligent problem-solving as integrated hierarchical reinforcement learning](https://mlsanity.com/paper/2208.08731/) (2022)
- [Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks](https://mlsanity.com/paper/2210.15629/) (2022)
- [DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics](https://mlsanity.com/paper/2312.06408/) (2023)
- [LARG, Language-based Automatic Reward and Goal Generation](https://mlsanity.com/paper/2306.10985/) (2023)
- [Trust in Language Grounding: a new AI challenge for human-robot teams](https://mlsanity.com/paper/2209.02066/) (2022)
- [Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action Corrections](https://mlsanity.com/paper/2211.10168/) (2022)
- [Cross-modality Force and Language Embeddings for Natural Human-Robot Communication](https://mlsanity.com/paper/2502.02772/) (2025)
- [DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2510.19562/) (2025)
- [mathrmE2CFD: Towards Effective and Efficient Cost Function Design for Safe Reinforcement Learning via Large Language Model](https://mlsanity.com/paper/2407.05580/) (2024)
- [From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models](https://mlsanity.com/paper/2409.16024/) (2024)

## Abstract (arXiv)

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.