mlsanityData to 14 Oct 2026

Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation

arXiv 2206.10606 ↗First posted 20 Jun 2022cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

In reality, it is often more efficient to ask for help than to search the entire space to find an object with an unknown location. We present a learning framework that enables an agent to actively ask for help in such embodied visual navigation tasks, where the feedback informs the agent of where the goal is in its view. To emulate the real-world scenario that a teacher may not always be present, we propose a training curriculum where feedback is not always available. We formulate an uncertainty measure of where the goal is and use empirical results to show that through this approach, the agent learns to ask for help effectively while remaining robust when feedback is not available.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 20 Jun 2022.

Builds on

38 of 51 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2017Deep reinforcement learning from human preferencescited by 3,912
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  7. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  8. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  9. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  10. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  11. 2020A Survey of Deep Active Learningcited by 554
  12. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
26 more
  1. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 366
  2. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 362
  3. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  4. 2019Vision-and-Dialog Navigationcited by 250
  5. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 244
  6. 2017Gate-Variants of Gated Recurrent Unit (GRU) Neural Networkscited by 242
  7. 2018Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environmentscited by 239
  8. 2021A Survey of Human-in-the-loop for Machine Learningcited by 215
  9. 2021TEACh: Task-driven Embodied Agents that Chatcited by 197
  10. 2021iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Taskscited by 194
  11. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  12. 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 193
  13. 2018Visual Semantic Navigation using Scene Priorscited by 128
  14. 2022Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directionscited by 117
  15. 2019Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learningcited by 100
  16. 2019Truly Proximal Policy Optimizationcited by 69
  17. 2022DialFRED: Dialogue-Enabled Agents for Embodied Instruction Followingcited by 63
  18. 2020An Exploration of Embodied Visual Explorationcited by 58
  19. 2020AllenAct: A Framework for Embodied AI Researchcited by 54
  20. 2019Just Ask:An Interactive Learning Framework for Vision and Language Navigationcited by 53
  21. 2019Leveraging Human Guidance for Deep Reinforcement Learning Taskscited by 42
  22. 2021A Survey on Interactive Reinforcement Learning: Design Principles and Open Challengescited by 41
  23. 2020Reinforcement learning with human advice: a surveycited by 24
  24. 2021A Framework for Learning to Request Rich and Contextually Useful Information from Humanscited by 12
  25. 2021Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scenecited by 7
  26. 2021Towards Interactive Reinforcement Learning with Intrinsic Feedbackcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024Learning to Ask: When LLM Agents Meet Unclear Instructioncited by 42
  2. 2025ADAPT: Actively Discovering and Adapting to Preferences for any Taskcited by 6
  3. 2026SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigationcited by 2