mlsanityData to 7 Oct 2026

Auxiliary Tasks Speed Up Learning PointGoal Navigation

arXiv 2007.04561 ↗First posted 9 Jul 2020cs.CV cs.LG cs.ROcited by 52

Not on the map. Why?

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.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 16; 2023: 14; 2024: 7; 2025: 2; 2026: 1.

52 papers.

Sort:

By area:

  1. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
  2. 2023Tool Learning with Foundation Modelscited by 302
  3. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  4. 2022Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scalecited by 116
  5. 2024GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigationcited by 93
  6. 2022Offline Visual Representation Learning for Embodied Navigationcited by 74
  7. 2021Auxiliary Tasks and Exploration Enable ObjectNavcited by 73
  8. 2022Housekeep: Tidying Virtual Households using Commonsense Reasoningcited by 57
  9. 2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 52
  10. 2021Curious Representation Learning for Embodied Intelligencecited by 43
  11. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 40
  12. 2022Is Mapping Necessary for Realistic PointGoal Navigation?cited by 32
38 more
  1. 2022Towards Versatile Embodied Navigationcited by 26
  2. 2024TANGO: Training-free Embodied AI Agents for Open-world Taskscited by 26
  3. 2022Last-Mile Embodied Visual Navigationcited by 25
  4. 2021GridToPix: Training Embodied Agents with Minimal Supervisioncited by 20
  5. 2023Selective Visual Representations Improve Convergence and Generalization for Embodied AIcited by 19
  6. 2022VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangementcited by 18
  7. 2022Ask4Help: Learning to Leverage an Expert for Embodied Taskscited by 18
  8. 2023Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigationcited by 18
  9. 2021Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigationcited by 17
  10. 2021Environment Predictive Coding for Embodied Agentscited by 12
  11. 2022AANG: Automating Auxiliary Learningcited by 12
  12. 2023MOPA: Modular Object Navigation with PointGoal Agentscited by 11
  13. 2023CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigationcited by 10
  14. 2024From Cognition to Precognition: A Future-Aware Framework for Social Navigationcited by 10
  15. 2022Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigationcited by 9
  16. 2023ENTL: Embodied Navigation Trajectory Learnercited by 9
  17. 2021Towards Disturbance-Free Visual Mobile Manipulationcited by 6
  18. 2022Exploiting Proximity-Aware Tasks for Embodied Social Navigationcited by 6
  19. 2023Learning with a Mole: Transferable latent spatial representations for navigation without reconstructioncited by 6
  20. 2025Federated Learning for Diffusion Modelscited by 6
  21. 2021Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challengecited by 5
  22. 2023Sequence-Agnostic Multi-Object Navigationcited by 5
  23. 2023Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Secondcited by 4
  24. 2023ALP: Action-Aware Embodied Learning for Perceptioncited by 4
  25. 2024Following the Human Thread in Social Navigationcited by 4
  26. 2025HomeSafeBench: Benchmarking Embodied Vision-Language Models in Free-Exploration Home Safety Inspectioncited by 4
  27. 2022A General Purpose Supervisory Signal for Embodied Agentscited by 3
  28. 2021Deep Learning for Embodied Vision Navigation: A Surveycited by 2
  29. 2022Embodied Navigation at the Art Gallerycited by 2
  30. 2024Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigationcited by 2
  31. 2024Reinforcement Learning via Auxiliary Task Distillationcited by 2
  32. 2024IN-Sight: Interactive Navigation through Sightcited by 2
  33. 2022A Simple Structure For Building A Robust Modelcited by 1
  34. 2022VI-PINNs: Variance-involved Physics-informed Neural Networks for Fast and Accurate Prediction of Partial Differential Equationscited by 1
  35. 2023Active Semantic Localization with Graph Neural Embeddingcited by 1
  36. 2026Self-Imitated Diffusion Policy for Efficient and Robust Visual Navigationcited by 1
  37. 2021Symmetry-aware Neural Architecture for Embodied Visual Navigationcited by 0
  38. 2022Structured Exploration Through Instruction Enhancement for Object Navigationcited by 0

50 most cited of 52 All 52 (JSON)