mlsanityData to 14 Oct 2026

Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation

arXiv 1803.07729 ↗First posted 21 Mar 2018cs.CV cs.AI cs.CLcited by 84

Not on the map. Why?

Abstract (arXiv)

Existing research studies on vision and language grounding for robot navigation focus on improving model-free deep reinforcement learning (DRL) models in synthetic environments. However, model-free DRL models do not consider the dynamics in the real-world environments, and they often fail to generalize to new scenes. In this paper, we take a radical approach to bridge the gap between synthetic studies and real-world practices---We propose a novel, planned-ahead hybrid reinforcement learning model that combines model-free and model-based reinforcement learning to solve a real-world vision-language navigation task. Our look-ahead module tightly integrates a look-ahead policy model with an environment model that predicts the next state and the reward. Experimental results suggest that our proposed method significantly outperforms the baselines and achieves the best on the real-world Room-to-Room dataset. Moreover, our scalable method is more generalizable when transferring to unseen environments.

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 2; 2019: 1; 2020: 0; 2021: 19; 2022: 21; 2023: 13; 2024: 14; 2025: 9; 2026: 5.

84 papers.

Sort:

By area:

  1. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  2. 2022SQA3D: Situated Question Answering in 3D Scenescited by 314
  3. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 305
  4. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 280
  5. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  6. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
  7. 2021Airbert: In-domain Pretraining for Vision-and-Language Navigationcited by 130
  8. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 122
  9. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 119
  10. 2022Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directionscited by 117
  11. 2019Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learningcited by 100
  12. 2024NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Modelscited by 98
38 more
  1. 2021Structured Scene Memory for Vision-Language Navigationcited by 95
  2. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 85
  3. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  4. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 72
  5. 2021Vision-Language Navigation with Random Environmental Mixupcited by 70
  6. 2022VLMbench: A Compositional Benchmark for Vision-and-Language Manipulationcited by 68
  7. 2021The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AIcited by 65
  8. 2023A2Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Modelscited by 62
  9. 2022Target-Driven Structured Transformer Planner for Vision-Language Navigationcited by 58
  10. 2022CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigationcited by 55
  11. 2022Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigationcited by 51
  12. 2021Neighbor-view Enhanced Model for Vision and Language Navigationcited by 50
  13. 2024Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environmentscited by 50
  14. 2021Scene-Intuitive Agent for Remote Embodied Visual Groundingcited by 49
  15. 2023Lana: A Language-Capable Navigator for Instruction Following and Generationcited by 40
  16. 2022Reinforced Structured State-Evolution for Vision-Language Navigationcited by 37
  17. 2021Diagnosing Vision-and-Language Navigation: What Really Matterscited by 36
  18. 2022On Transforming Reinforcement Learning by Transformer: The Development Trajectorycited by 36
  19. 2021Vision-Language Navigation: A Survey and Taxonomycited by 34
  20. 2025CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memorycited by 32
  21. 2021Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Informationcited by 31
  22. 2021Core Challenges in Embodied Vision-Language Planningcited by 30
  23. 2021A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learningcited by 27
  24. 2022Prompt-based Learning for Unpaired Image Captioningcited by 23
  25. 2022FOAM: A Follower-aware Speaker Model For Vision-and-Language Navigationcited by 22
  26. 2021GridToPix: Training Embodied Agents with Minimal Supervisioncited by 21
  27. 2024Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigationcited by 20
  28. 2024Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactionscited by 19
  29. 2024Vision-Language Navigation with Energy-Based Policycited by 19
  30. 2021Curriculum Learning for Vision-and-Language Navigationcited by 18
  31. 2024SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Expertscited by 16
  32. 2022ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Rewardcited by 11
  33. 2023MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigationcited by 11
  34. 2022CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representationscited by 10
  35. 2023ESceme: Vision-and-Language Navigation with Episodic Scene Memorycited by 10
  36. 2024Guide-LLM: An Embodied LLM Agent and Text-Based Topological Map for Robotic Guidance of People with Visual Impairmentscited by 10
  37. 2023Graph based Environment Representation for Vision-and-Language Navigation in Continuous Environmentscited by 9
  38. 2024Vision-Language Navigation with Embodied Intelligence: A Surveycited by 9

50 most cited of 84 All 84 (JSON)