# Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks

arXiv: https://arxiv.org/abs/1709.00507 · HTML: https://mlsanity.com/paper/1709.00507/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2017.

## Built on by (most cited first, 30 of 38)

- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [Memory-Augmented Reinforcement Learning for Image-Goal Navigation](https://mlsanity.com/paper/2101.05181/) (2021)
- [SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency](https://mlsanity.com/paper/2112.01001/) (2021)
- [ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning](https://mlsanity.com/paper/2505.21457/) (2025)
- [Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds](https://mlsanity.com/paper/2111.14843/) (2021)
- [Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop](https://mlsanity.com/paper/2506.10968/) (2025)
- [A Survey on Human-aware Robot Navigation](https://mlsanity.com/paper/2106.11650/) (2021)
- [Embodied AI: From LLMs to World Models](https://mlsanity.com/paper/2509.20021/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [EgoEnv: Human-centric environment representations from egocentric video](https://mlsanity.com/paper/2207.11365/) (2022)
- [Learning Active Camera for Multi-Object Navigation](https://mlsanity.com/paper/2210.07505/) (2022)
- [Pay Self-Attention to Audio-Visual Navigation](https://mlsanity.com/paper/2210.01353/) (2022)
- [Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task](https://mlsanity.com/paper/2211.05039/) (2022)
- [Environment Predictive Coding for Embodied Agents](https://mlsanity.com/paper/2102.02337/) (2021)
- [Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration](https://mlsanity.com/paper/2108.11717/) (2021)
- [Learning to Act with Affordance-Aware Multimodal Neural SLAM](https://mlsanity.com/paper/2201.09862/) (2022)
- [Embodied Active Learning of Relational State Abstractions for Bilevel Planning](https://mlsanity.com/paper/2303.04912/) (2023)
- [Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos](https://mlsanity.com/paper/2411.08753/) (2024)
- [Believing is Seeing: Unobserved Object Detection using Generative Models](https://mlsanity.com/paper/2410.05869/) (2024)
- [Distribution Guided Active Feature Acquisition](https://mlsanity.com/paper/2410.03915/) (2024)
- [i-PhysGaussian: Implicit Physical Simulation for 3D Gaussian Splatting](https://mlsanity.com/paper/2602.17117/) (2026)
- [Visual Attention in Imaginative Agents](https://mlsanity.com/paper/2104.00177/) (2021)
- [FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty](https://mlsanity.com/paper/2204.01267/) (2022)
- [TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration](https://mlsanity.com/paper/2311.15335/) (2023)
- [Towards Cost Sensitive Decision Making](https://mlsanity.com/paper/2410.03892/) (2024)
- [Apple: Toward General Active Perception via Reinforcement Learning](https://mlsanity.com/paper/2505.06182/) (2025)
- [An Approach to Partial Observability in Games: Learning to Both Act and Observe](https://mlsanity.com/paper/2108.05701/) (2021)
- [Symmetry-aware Neural Architecture for Embodied Visual Navigation](https://mlsanity.com/paper/2112.09515/) (2021)

## Abstract (arXiv)

It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to look around: if a visual agent has the ability to voluntarily acquire new views to observe its environment, how can it learn efficient exploratory behaviors to acquire informative observations? We propose a reinforcement learning solution, where the agent is rewarded for actions that reduce its uncertainty about the unobserved portions of its environment. Based on this principle, we develop a recurrent neural network-based approach to perform active completion of panoramic natural scenes and 3D object shapes. Crucially, the learned policies are not tied to any recognition task nor to the particular semantic content seen during training. As a result, 1) the learned "look around" behavior is relevant even for new tasks in unseen environments, and 2) training data acquisition involves no manual labeling. Through tests in diverse settings, we demonstrate that our approach learns useful generic policies that transfer to new unseen tasks and environments. Completion episodes are shown at https://goo.gl/BgWX3W.