mlsanityData to 14 Oct 2026

Learning to Navigate in Complex Environments

arXiv 1611.03673 ↗First posted 11 Nov 2016cs.AI cs.CV cs.LGcited by 198

Not on the map. Why?

Cited by 27 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinforcement learning problem and show that data efficiency and task performance can be dramatically improved by relying on additional auxiliary tasks leveraging multimodal sensory inputs. In particular we consider jointly learning the goal-driven reinforcement learning problem with auxiliary depth prediction and loop closure classification tasks. This approach can learn to navigate from raw sensory input in complicated 3D mazes, approaching human-level performance even under conditions where the goal location changes frequently. We provide detailed analysis of the agent behaviour, its ability to localise, and its network activity dynamics, showing that the agent implicitly learns key navigation abilities.

Key facts. Cited by 198 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Nov 2016.

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: 2; 2021: 52; 2022: 42; 2023: 30; 2024: 27; 2025: 25; 2026: 17.

198 papers.

Sort:

By area:

  1. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 305
  2. 2024Navigation World Modelscited by 272
  3. 2022Masked Visual Pre-training for Motor Controlcited by 248
  4. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 212
  5. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 170
  6. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 166
  7. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 131
  8. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  9. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 122
  10. 2022Navigating to Objects in the Real Worldcited by 106
  11. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 105
  12. 2021ManipulaTHOR: A Framework for Visual Object Manipulationcited by 102
38 more
  1. 2021Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformerscited by 79
  2. 2021Auxiliary Tasks and Exploration Enable ObjectNavcited by 74
  3. 2024DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Drivingcited by 67
  4. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 66
  5. 2021The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AIcited by 65
  6. 2021On The Effect of Auxiliary Tasks on Representation Dynamicscited by 57
  7. 2021Deep Federated Learning for Autonomous Drivingcited by 54
  8. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 52
  9. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 51
  10. 2021Scene-Intuitive Agent for Remote Embodied Visual Groundingcited by 49
  11. 2022Retrospectives on the Embodied AI Workshopcited by 46
  12. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 43
  13. 2021Augmenting Automated Game Testing with Deep Reinforcement Learningcited by 38
  14. 2021Return-Based Contrastive Representation Learning for Reinforcement Learningcited by 36
  15. 2021Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomizationcited by 35
  16. 2024360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roamingcited by 35
  17. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34
  18. 2022Chain of Thought Imitation with Procedure Cloningcited by 30
  19. 2022Towards Versatile Embodied Navigationcited by 26
  20. 2024Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructionscited by 25
  21. 2019Learning Belief Representations for Imitation Learning in POMDPscited by 24
  22. 2021Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Surveycited by 24
  23. 2021Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomizationcited by 23
  24. 2022Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learningcited by 22
  25. 2022Multi-Object Navigation with dynamically learned neural implicit representationscited by 21
  26. 2022Transferable and Adaptable Driving Behavior Predictioncited by 20
  27. 2022Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machinescited by 20
  28. 2022Search for or Navigate to? Dual Adaptive Thinking for Object Navigationcited by 20
  29. 2021Learning Efficient Multi-Agent Cooperative Visual Explorationcited by 19
  30. 2023Selective Visual Representations Improve Convergence and Generalization for Embodied AIcited by 19
  31. 2022Unbiased Directed Object Attention Graph for Object Navigationcited by 18
  32. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  33. 2022Pay Self-Attention to Audio-Visual Navigationcited by 18
  34. 2021Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigationcited by 17
  35. 2021Structure from Silence: Learning Scene Structure from Ambient Soundcited by 17
  36. 2022Navigating to Objects in Unseen Environments by Distance Predictioncited by 16
  37. 2022Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiencycited by 16
  38. 2023End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenoncited by 16

50 most cited of 198 All 198 (JSON)