mlsanityData to 7 Oct 2026

120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL

arXiv 2603.26441 ↗First posted 27 Mar 2026cs.ROcited by 0

On the map: Offline RL and imitation learning from data → Language-conditioned policies and VLAs

Abstract (arXiv)

The prevailing paradigm for image-goal visual navigation often assumes access to large-scale datasets, substantial pretraining, and significant computational resources. In this work, we challenge this assumption. We show that we can collect a dataset, train an in-domain policy, and deploy it to the real world (1) in less than 120 minutes, (2) on a consumer laptop, (3) without any human intervention. Our method, MINav, formulates image-goal navigation as an offline goal-conditioned reinforcement learning problem, combining unsupervised data collection with hindsight goal relabeling and offline policy learning. Experiments in simulation and the real world show that MINav improves exploration efficiency, outperforms zero-shot navigation baselines in target environments, and scales favorably with dataset size. These results suggest that effective real-world robotic learning can be achieved with high computational efficiency, lowering the barrier to rapid policy prototyping and deployment.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Language-conditioned policies and VLAs, one of 13 directions in Offline RL and imitation learning from data. Builds on 25 of its 29 references that are in the map. First posted on arXiv 27 Mar 2026.

Builds on

25 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Offline Reinforcement Learning for Visual Navigation16 Dec

Other references · 24

  1. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  3. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  4. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  5. 2025DINOv3cited by 1,297
  6. 2017Hindsight Experience Replaycited by 1,096
  7. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  8. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  9. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 435
  10. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  11. 2025π*0.6: a VLA That Learns From Experiencecited by 280
  12. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
12 more
  1. 2023NoMaD: Goal Masked Diffusion Policies for Navigation and Explorationcited by 234
  2. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 216
  3. 2023ViNT: A Foundation Model for Visual Navigationcited by 210
  4. 2022GNM: A General Navigation Model to Drive Any Robotcited by 161
  5. 2022Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instancescited by 53
  6. 2023Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigationcited by 25
  7. 2023The Generalization Gap in Offline Reinforcement Learningcited by 25
  8. 2022Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performancecited by 21
  9. 2020Embodied Visual Navigation with Automatic Curriculum Learning in Real Environmentscited by 20
  10. 2025General Scene Adaptation for Vision-and-Language Navigationcited by 17
  11. 2022Real World Offline Reinforcement Learning with Realistic Data Sourcecited by 16
  12. 2025Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filteringcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
  2. 2022Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning
  3. 2026NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation
  4. 2026Less Is More: Scalable Visual Navigation from Limited Data
  5. 2018Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrations
  6. 2026Latent World Models with Monotone Planning Costs for Image-Goal Navigation
  7. 2025What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
  8. 2017One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay