Multimodal Vision Research Laboratory MVRL

Research Area: Reinforcement Learning

How should an agent search visual or geospatial space when observations are partial and costly? Our reinforcement learning research targets active search, exploration, and sequential decision-making in visual domains. Recent work includes diffusion-guided visual active search in partially observable environments (DiffVAS), goal modality agnostic active geo-localization (GOMAA-Geo), and partially-supervised frameworks for visual active search. We study interpretable policies, hindsight-observable POMDPs, and learning from limited supervision—often paired with geospatial embeddings and localization methods for real-world deployment.

View All Publications →

All Publications

  1. Thumbnail for DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments
    Sarkar A, Sastry S, Pirinen A, Jacobs N, Vorobeychik Y. 2026. DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS).
    paper bibtex Reinforcement Learning GeoAI GenAI
  2. Thumbnail for Active Geospatial Search for Efficient Tenant Eviction Outreach
    Sarkar A, DiChristofano A, Das S, Fowler PJ, Jacobs N, Vorobeychik Y. 2025. Active Geospatial Search for Efficient Tenant Eviction Outreach. In: AAAI Conference on Artificial Intelligence (AAAI). 28340–28348.
    code paper bibtex Reinforcement Learning GeoAI Urban
  3. Thumbnail for GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
    Sarkar A, Sastry S, Pirinen A, Zhang C, Jacobs N, Vorobeychik Y. 2024. GOMAA-Geo: GOal Modality Agnostic Active Geo-localization. In: Neural Information Processing Systems (NeurIPS).
    code paper bibtex Reinforcement Learning Vision-Language Localization GeoAI
  4. Thumbnail for Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning
    Lanier M, Xu Y, Jacobs N, Zhang C, Vorobeychik Y. 2024. Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning. In: IEEE International Conference on Machine Learning and Applications.
    paper bibtex Reinforcement Learning
  5. Hormozabad SJ, Jacobs N, Soto MG. 2024. Reinforcement Learning for Integrated Structural Control and Health Monitoring. Practice Periodical on Structural Design and Construction 29. DOI: 10.1061/PPSCFX.SCENG-1455.
    doi bibtex Reinforcement Learning
  6. Sarkar A, DiChristofano A, Das S, Fowler P, Jacobs N, Vorobeychik Y. 2024. Geospatial Active Search for Preventing Evictions. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS).
    bibtex Reinforcement Learning GeoAI Urban
  7. Thumbnail for A Visual Active Search Framework for Geospatial Exploration
    Sarkar A, Lanier M, Alfeld S, Feng J, Garnett R, Jacobs N, Vorobeychik Y. 2024. A Visual Active Search Framework for Geospatial Exploration. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
    code paper press bibtex Reinforcement Learning GeoAI
  8. Thumbnail for A Partially-Supervised Reinforcement Learning Framework for Visual Active Search
    Sarkar A, Jacobs N, Vorobeychik Y. 2023. A Partially-Supervised Reinforcement Learning Framework for Visual Active Search. In: Neural Information Processing Systems (NeurIPS).
    code paper press bibtex Reinforcement Learning GeoAI