Learning Q-network for Active Information Acquisition

TL;DR

This paper introduces a reinforcement learning framework for active information acquisition that does not rely on known models, enabling real-time, long-horizon planning for robotic sensor management.

Contribution

It presents a model-free RL approach for active information gathering, overcoming limitations of traditional planning methods in long-horizon and model-dependent scenarios.

Findings

RL-based policies outperform traditional methods in multi-target tracking.

The approach enables real-time control without prior knowledge of models.

Long-horizon planning benefits from reinforcement learning's discounted reward optimization.

Abstract

In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors. The classic challenges in the information acquisition problem are the dependence of a planning algorithm on known models and the difficulty of computing information-theoretic cost functions over arbitrary distributions. In contrast, the proposed framework of reinforcement learning does not require any knowledge on models and alleviates the problems during an extended training stage. It results in policies that are efficient to execute online and applicable for real-time control of robotic systems. Furthermore, the state-of-the-art planning methods are typically restricted to short horizons, which may become problematic with local minima. Reinforcement learning naturally handles the issue of planning horizon in information problems as it maximizes a discounted sum of rewards over a long finite or infinite time horizon. We discuss the potential benefits of the proposed framework and compare the performance of the novel algorithm to an existing information acquisition method for multi-target tracking scenarios.