Timezone: »

REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis
Yu-Shao Peng · Kai-Fu Tang · Hsuan-Tien Lin · Edward Chang

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #115

This paper proposes REFUEL, a reinforcement learning method with two techniques: {\em reward shaping} and {\em feature rebuilding}, to improve the performance of online symptom checking for disease diagnosis. Reward shaping can guide the search of policy towards better directions. Feature rebuilding can guide the agent to learn correlations between features. Together, they can find symptom queries that can yield positive responses from a patient with high probability. Experimental results justify that the two techniques in REFUEL allows the symptom checker to identify the disease more rapidly and accurately.

Author Information

Yu-Shao Peng (HTC Research)
Kai-Fu Tang (HTC Research)
Hsuan-Tien Lin (Appier/National Taiwan University)
Edward Chang

More from the Same Authors