Lecture
This lecture presents strategies for long-horizon robot exploration in continuous action spaces, focusing on multi-object search. The approach combines long-horizon thinking with short-horizon control, extending multi-object search to continuous action spaces. The lecture details the architecture, where a predictive head guides the direction to the next closest object, and the policy can follow or deviate from long-horizon goals. Results from training and testing in different environments are discussed, showcasing the effectiveness of the proposed approach.