# Auxiliary Tasks Speed Up Learning PointGoal Navigation

arXiv: https://arxiv.org/abs/2007.04561 · HTML: https://mlsanity.com/paper/2007.04561/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2020.

## Built on by (most cited first, 30 of 54)

- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale](https://mlsanity.com/paper/2204.03514/) (2022)
- [GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation](https://mlsanity.com/paper/2404.06609/) (2024)
- [Offline Visual Representation Learning for Embodied Navigation](https://mlsanity.com/paper/2204.13226/) (2022)
- [Auxiliary Tasks and Exploration Enable ObjectNav](https://mlsanity.com/paper/2104.04112/) (2021)
- [Housekeep: Tidying Virtual Households using Commonsense Reasoning](https://mlsanity.com/paper/2205.10712/) (2022)
- [RobustNav: Towards Benchmarking Robustness in Embodied Navigation](https://mlsanity.com/paper/2106.04531/) (2021)
- [Curious Representation Learning for Embodied Intelligence](https://mlsanity.com/paper/2105.01060/) (2021)
- [Learning Navigational Visual Representations with Semantic Map Supervision](https://mlsanity.com/paper/2307.12335/) (2023)
- [Is Mapping Necessary for Realistic PointGoal Navigation?](https://mlsanity.com/paper/2206.00997/) (2022)
- [TANGO: Training-free Embodied AI Agents for Open-world Tasks](https://mlsanity.com/paper/2412.10402/) (2024)
- [Towards Versatile Embodied Navigation](https://mlsanity.com/paper/2210.16822/) (2022)
- [Last-Mile Embodied Visual Navigation](https://mlsanity.com/paper/2211.11746/) (2022)
- [GridToPix: Training Embodied Agents with Minimal Supervision](https://mlsanity.com/paper/2105.00931/) (2021)
- [Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation](https://mlsanity.com/paper/2308.10306/) (2023)
- [Selective Visual Representations Improve Convergence and Generalization for Embodied AI](https://mlsanity.com/paper/2311.04193/) (2023)
- [VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement](https://mlsanity.com/paper/2210.05064/) (2022)
- [Ask4Help: Learning to Leverage an Expert for Embodied Tasks](https://mlsanity.com/paper/2211.09960/) (2022)
- [Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation](https://mlsanity.com/paper/2107.06011/) (2021)
- [Environment Predictive Coding for Embodied Agents](https://mlsanity.com/paper/2102.02337/) (2021)
- [AANG: Automating Auxiliary Learning](https://mlsanity.com/paper/2205.14082/) (2022)
- [ENTL: Embodied Navigation Trajectory Learner](https://mlsanity.com/paper/2304.02639/) (2023)
- [MOPA: Modular Object Navigation with PointGoal Agents](https://mlsanity.com/paper/2304.03696/) (2023)
- [CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation](https://mlsanity.com/paper/2306.10322/) (2023)
- [From Cognition to Precognition: A Future-Aware Framework for Social Navigation](https://mlsanity.com/paper/2409.13244/) (2024)
- [Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation](https://mlsanity.com/paper/2211.11116/) (2022)
- [Federated Learning for Diffusion Models](https://mlsanity.com/paper/2503.06426/) (2025)
- [Towards Disturbance-Free Visual Mobile Manipulation](https://mlsanity.com/paper/2112.12612/) (2021)

## Abstract (arXiv)

PointGoal Navigation is an embodied task that requires agents to navigate to a specified point in an unseen environment. Wijmans et al. showed that this task is solvable but their method is computationally prohibitive, requiring 2.5 billion frames and 180 GPU-days. In this work, we develop a method to significantly increase sample and time efficiency in learning PointNav using self-supervised auxiliary tasks (e.g. predicting the action taken between two egocentric observations, predicting the distance between two observations from a trajectory,etc.).We find that naively combining multiple auxiliary tasks improves sample efficiency,but only provides marginal gains beyond a point. To overcome this, we use attention to combine representations learnt from individual auxiliary tasks. Our best agent is 5.5x faster to reach the performance of the previous state-of-the-art, DD-PPO, at 40M frames, and improves on DD-PPO's performance at 40M frames by 0.16 SPL. Our code is publicly available at https://github.com/joel99/habitat-pointnav-aux.