# Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents

arXiv: https://arxiv.org/abs/1805.08329 · HTML: https://mlsanity.com/paper/1805.08329/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2018.

## Built on by (most cited first, 5 of 5)

- [Vision-Language Navigation: A Survey and Taxonomy](https://mlsanity.com/paper/2108.11544/) (2021)
- [Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines](https://mlsanity.com/paper/2205.11558/) (2022)
- [Towards Navigation by Reasoning over Spatial Configurations](https://mlsanity.com/paper/2105.06839/) (2021)
- [A Framework for Learning to Request Rich and Contextually Useful Information from Humans](https://mlsanity.com/paper/2110.08258/) (2021)
- [Reinforcement Learning of Implicit and Explicit Control Flow in Instructions](https://mlsanity.com/paper/2102.13195/) (2021)

## Abstract (arXiv)

Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning. In this paper, we propose a simple but effective neural language grounding module for embodied agents that can be trained end to end from scratch taking raw pixels, unstructured linguistic commands, and sparse rewards as the inputs. We model the language grounding process as a language-guided transformation of visual features, where latent sentence embeddings are used as the transformation matrices. In several language-directed navigation tasks that feature challenging partial observability and require simple reasoning, our module significantly outperforms the state of the art. We also release XWorld3D, an easy-to-customize 3D environment that can potentially be modified to evaluate a variety of embodied agents.