Perspective view of autonomous control in unknown environment: Dual control for exploitation and exploration vs reinforcement learning

A deep reinforcement learning based searching method for source localization

Concurrent Active Learning in Autonomous Airborne Source Search: Dual Control for Exploration and Exploitation

Autonomous Source Seeking and Estimation via Active Information-Directed Reinforcement Learning

Source Term Estimation Using Deep Reinforcement Learning With Gaussian Mixture Model Feature Extraction for Mobile Sensors

Robotic Information Gathering With Reinforcement Learning Assisted by Domain Knowledge: An Application to Gas Source Localization