Emergence of Exploratory Look-Around Behaviors through Active Observation Completion
This addresses the challenge of autonomous observation capture for agents in computer vision, though it is incremental as it builds on existing reinforcement learning methods.
The paper tackles the problem of enabling agents to autonomously capture informative visual observations by learning to look around, using reinforcement learning with a reward based on reducing uncertainty about unobserved parts of the environment, and it shows that the learned policies generalize to active perception tasks.
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.