# Sidekick Policy Learning for Active Visual Exploration

arXiv: https://arxiv.org/abs/1807.11010 · HTML: https://mlsanity.com/paper/1807.11010/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2018.

## Built on by (most cited first, 11 of 11)

- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [LiDAR-based 4D Occupancy Completion and Forecasting](https://mlsanity.com/paper/2310.11239/) (2023)
- [Learning Active Camera for Multi-Object Navigation](https://mlsanity.com/paper/2210.07505/) (2022)
- [Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception](https://mlsanity.com/paper/2311.13793/) (2023)
- [Active Visual Exploration Based on Attention-Map Entropy](https://mlsanity.com/paper/2303.06457/) (2023)
- [Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration](https://mlsanity.com/paper/2108.11717/) (2021)
- [Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos](https://mlsanity.com/paper/2411.08753/) (2024)
- [Next-Gen Machine Learning Supported Diagnostic Systems for Spacecraft](https://mlsanity.com/paper/2106.05659/) (2021)
- [FindView: Precise Target View Localization Task for Look Around Agents](https://mlsanity.com/paper/2303.09054/) (2023)
- [Deep Active Perception for Object Detection using Navigation Proposals](https://mlsanity.com/paper/2312.10200/) (2023)
- [Visual Episodic Memory-based Exploration](https://mlsanity.com/paper/2405.11298/) (2024)

## Abstract (arXiv)

We consider an active visual exploration scenario, where an agent must intelligently select its camera motions to efficiently reconstruct the full environment from only a limited set of narrow field-of-view glimpses. While the agent has full observability of the environment during training, it has only partial observability once deployed, being constrained by what portions it has seen and what camera motions are permissible. We introduce sidekick policy learning to capitalize on this imbalance of observability. The main idea is a preparatory learning phase that attempts simplified versions of the eventual exploration task, then guides the agent via reward shaping or initial policy supervision. To support interpretation of the resulting policies, we also develop a novel policy visualization technique. Results on active visual exploration tasks with 360 scenes and 3D objects show that sidekicks consistently improve performance and convergence rates over existing methods. Code, data and demos are available.