# Emergence of Exploratory Look-Around Behaviors through Active Observation Completion

arXiv: https://arxiv.org/abs/1906.11407 · HTML: https://mlsanity.com/paper/1906.11407/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2019.

## Built on by (most cited first, 14 of 14)

- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [A Survey on Human-aware Robot Navigation](https://mlsanity.com/paper/2106.11650/) (2021)
- [Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception](https://mlsanity.com/paper/2311.13793/) (2023)
- [Environment Predictive Coding for Embodied Agents](https://mlsanity.com/paper/2102.02337/) (2021)
- [Learning to See Physical Properties with Active Sensing Motor Policies](https://mlsanity.com/paper/2311.01405/) (2023)
- [WoMAP: World Models For Embodied Open-Vocabulary Object Localization](https://mlsanity.com/paper/2506.01600/) (2025)
- [Full-Body Visual Self-Modeling of Robot Morphologies](https://mlsanity.com/paper/2111.06389/) (2021)
- [Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos](https://mlsanity.com/paper/2411.08753/) (2024)
- [Visual Attention in Imaginative Agents](https://mlsanity.com/paper/2104.00177/) (2021)
- [Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy](https://mlsanity.com/paper/2210.09435/) (2022)
- [Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos](https://mlsanity.com/paper/2412.18386/) (2024)
- [FindView: Precise Target View Localization Task for Look Around Agents](https://mlsanity.com/paper/2303.09054/) (2023)
- [LEAP: Learning Emergent Active Perception for Quadruped Navigation](https://mlsanity.com/paper/2609.17628/) (2026)

## Abstract (arXiv)

Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to look around: how can an agent learn to acquire informative visual observations? We propose a reinforcement learning solution, where the agent is rewarded for reducing its uncertainty about the unobserved portions of its environment. Specifically, the agent is trained to select a short sequence of glimpses after which it must infer the appearance of its full environment. To address the challenge of sparse rewards, we further introduce sidekick policy learning, which exploits the asymmetry in observability between training and test time. The proposed methods learn observation policies that not only perform the completion task for which they are trained, but also generalize to exhibit useful "look-around" behavior for a range of active perception tasks.