no code implementations • 29 Sep 2021 • Khanh Xuan Nguyen, Yonatan Bisk, Hal Daumé III
Results on a simulated human-assisted navigation problem demonstrate the effectiveness of our framework: aided with an interaction policy learned by our method, a navigation policy achieves up to a 7× improvement in task success rate compared to performing tasks only by itself.
Hierarchical Reinforcement Learning reinforcement-learning +1