# Neural Modular Control for Embodied Question Answering

arXiv: https://arxiv.org/abs/1810.11181 · HTML: https://mlsanity.com/paper/1810.11181/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2018.

## Built on by (most cited first, 30 of 56)

- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments](https://mlsanity.com/paper/2108.03332/) (2021)
- [Waypoint Models for Instruction-guided Navigation in Continuous Environments](https://mlsanity.com/paper/2110.02207/) (2021)
- [PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav](https://mlsanity.com/paper/2301.07302/) (2023)
- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention](https://mlsanity.com/paper/1812.04155/) (2018)
- [Explore until Confident: Efficient Exploration for Embodied Question Answering](https://mlsanity.com/paper/2403.15941/) (2024)
- [ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation](https://mlsanity.com/paper/2409.13682/) (2024)
- [Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring](https://mlsanity.com/paper/2106.03427/) (2021)
- [Generating Human Motion in 3D Scenes from Text Descriptions](https://mlsanity.com/paper/2405.07784/) (2024)
- [ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning](https://mlsanity.com/paper/2505.21457/) (2025)
- [ELLA: Exploration through Learned Language Abstraction](https://mlsanity.com/paper/2103.05825/) (2021)
- [Vision-Language Navigation: A Survey and Taxonomy](https://mlsanity.com/paper/2108.11544/) (2021)
- [Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents](https://mlsanity.com/paper/2308.07241/) (2023)
- [AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant](https://mlsanity.com/paper/2203.04203/) (2022)
- [Core Challenges in Embodied Vision-Language Planning](https://mlsanity.com/paper/2106.13948/) (2021)
- [TANGO: Training-free Embodied AI Agents for Open-world Tasks](https://mlsanity.com/paper/2412.10402/) (2024)
- [One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones](https://mlsanity.com/paper/2202.07028/) (2022)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [GridToPix: Training Embodied Agents with Minimal Supervision](https://mlsanity.com/paper/2105.00931/) (2021)
- [Ground then Navigate: Language-guided Navigation in Dynamic Scenes](https://mlsanity.com/paper/2209.11972/) (2022)
- [End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon](https://mlsanity.com/paper/2309.16634/) (2023)
- [EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering](https://mlsanity.com/paper/2410.20263/) (2024)
- [Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering](https://mlsanity.com/paper/2507.12846/) (2025)
- [Memory-Centric Embodied Question Answering](https://mlsanity.com/paper/2505.13948/) (2025)
- [Visual Adversarial Attacks and Defenses in the Physical World: A Survey](https://mlsanity.com/paper/2211.01671/) (2022)
- [NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries](https://mlsanity.com/paper/2412.10726/) (2024)
- [When Robots Should Say "I Don't Know": Benchmarking Abstention in Embodied Question Answering](https://mlsanity.com/paper/2512.04597/) (2025)

## Abstract (arXiv)

We present a modular approach for learning policies for navigation over long planning horizons from language input. Our hierarchical policy operates at multiple timescales, where the higher-level master policy proposes subgoals to be executed by specialized sub-policies. Our choice of subgoals is compositional and semantic, i.e. they can be sequentially combined in arbitrary orderings, and assume human-interpretable descriptions (e.g. 'exit room', 'find kitchen', 'find refrigerator', etc.). We use imitation learning to warm-start policies at each level of the hierarchy, dramatically increasing sample efficiency, followed by reinforcement learning. Independent reinforcement learning at each level of hierarchy enables sub-policies to adapt to consequences of their actions and recover from errors. Subsequent joint hierarchical training enables the master policy to adapt to the sub-policies. On the challenging EQA (Das et al., 2018) benchmark in House3D (Wu et al., 2018), requiring navigating diverse realistic indoor environments, our approach outperforms prior work by a significant margin, both in terms of navigation and question answering.