mlsanityData to 7 Oct 2026

Learning Exploration Policies for Navigation

arXiv 1903.01959 ↗First posted 5 Mar 2019cs.RO cs.AI cs.LGcited by 113

Not on the map. Why?

Abstract (arXiv)

Numerous past works have tackled the problem of task-driven navigation. But, how to effectively explore a new environment to enable a variety of down-stream tasks has received much less attention. In this work, we study how agents can autonomously explore realistic and complex 3D environments without the context of task-rewards. We propose a learning-based approach and investigate different policy architectures, reward functions, and training paradigms. We find that the use of policies with spatial memory that are bootstrapped with imitation learning and finally finetuned with coverage rewards derived purely from on-board sensors can be effective at exploring novel environments. We show that our learned exploration policies can explore better than classical approaches based on geometry alone and generic learning-based exploration techniques. Finally, we also show how such task-agnostic exploration can be used for down-stream tasks. Code and Videos are available at: https://sites.google.com/view/exploration-for-nav.

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 24; 2022: 35; 2023: 19; 2024: 21; 2025: 8; 2026: 5.

113 papers.

Sort:

By area:

  1. 2024Navigation World Modelscited by 262
  2. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  3. 2023NoMaD: Goal Masked Diffusion Policies for Navigation and Explorationcited by 234
  4. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  5. 2022Open-vocabulary Queryable Scene Representations for Real World Planningcited by 159
  6. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 149
  7. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 127
  8. 2022Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scalecited by 116
  9. 2021Visual Room Rearrangementcited by 101
  10. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  11. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 64
  12. 2021The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AIcited by 64
38 more
  1. 2021No RL, No Simulation: Learning to Navigate without Navigatingcited by 63
  2. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  3. 2023Renderable Neural Radiance Map for Visual Navigationcited by 51
  4. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 50
  5. 2021Learning to Map for Active Semantic Goal Navigationcited by 47
  6. 2022NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fieldscited by 41
  7. 2024GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstructioncited by 39
  8. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34
  9. 2022Uncertainty-driven Planner for Exploration and Navigationcited by 31
  10. 2022Stubborn: A Strong Baseline for Indoor Object Navigationcited by 31
  11. 2022TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priorscited by 30
  12. 2024SPIN: Simultaneous Perception, Interaction and Navigationcited by 27
  13. 2022Last-Mile Embodied Visual Navigationcited by 25
  14. 2024RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigationcited by 25
  15. 2024Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigationcited by 24
  16. 2021Causal Navigation by Continuous-time Neural Networkscited by 23
  17. 2021Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learningcited by 23
  18. 2022EgoEnv: Human-centric environment representations from egocentric videocited by 22
  19. 2022Learning Active Camera for Multi-Object Navigationcited by 20
  20. 2021Learning Efficient Multi-Agent Cooperative Visual Explorationcited by 19
  21. 2024Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Modelcited by 19
  22. 2022Ask4Help: Learning to Leverage an Expert for Embodied Taskscited by 18
  23. 2021Shaping embodied agent behavior with activity-context priors from egocentric videocited by 17
  24. 2022Pay Self-Attention to Audio-Visual Navigationcited by 17
  25. 2023Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Explorationcited by 17
  26. 2024OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representationcited by 17
  27. 2024ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environmentscited by 16
  28. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  29. 2022Navigating to Objects in Unseen Environments by Distance Predictioncited by 15
  30. 2022N2M2: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environmentscited by 15
  31. 2020Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learningcited by 14
  32. 2023Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedbackcited by 13
  33. 2024MemoNav: Working Memory Model for Visual Navigationcited by 13
  34. 2021Environment Predictive Coding for Embodied Agentscited by 12
  35. 2023Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulationcited by 12
  36. 2021MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigationcited by 11
  37. 2023MOPA: Modular Object Navigation with PointGoal Agentscited by 11
  38. 2023AcTExplore: Active Tactile Exploration of Unknown Objectscited by 11

50 most cited of 113 All 113 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2020Learning Navigation Costs from Demonstration in Partially Observable Environments
  2. 2026Look Before You Leap: Autonomous Exploration for LLM Agents
  3. 2023Learning to Navigate from Scratch using World Models and Curiosity: the Good, the Bad, and the Ugly
  4. 2025CompassNav: Steering From Path Imitation To Decision Understanding In Navigation
  5. 2018Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrations
  6. 2017One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay
  7. 2026120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL
  8. 2021Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning