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

## TL;DR

This paper presents a reinforcement learning approach for agents to actively explore and observe their environment efficiently, learning to look around and infer unobserved areas through reward-based training.

## Contribution

It introduces a novel reinforcement learning framework with sidekick policy learning for active observation and environment inference in vision systems.

## Key findings

- Agents learn effective look-around behaviors
- Observation policies generalize to various perception tasks
- Improved environment inference accuracy

## Abstract

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.