Dr. WANG Bing from the University of New South Wales (Australia) was invited by the CAS Key Laboratory of Speech Acoustics and Content Understanding this Monday to present her research findings to staff and students of our institute. Dr. WANG’s presentation was named “Autonomous Hypothesis Generation as an Environment Learning Mechanism for Agent Design”. 

Dr. WANG first defined a novel autonomous hypothesis generation problem to enable an agent to model its general environment with limited human involvement. And then, she introduced two algorithms as its solutions. 

Studies on agent design have been focused on the internal structure of an agent that facilities decision-making subject to domain specific tasks. The domain and environment knowledge of an artificial agent is often hard coded by system engineers, which is both time-consuming and task dependent. 

Her experiments given in the presentation showed that an agent using the proposed algorithm was able to correctly reconstruct its environment model to a certain extent. 

After the talk, the attendees had a lively discussion with Dr. WANG about the challenges in Autonomous Hypothesis Generation theory and possible applications.

(Source: XU Weiqun from the CAS Key Laboratory of Speech Acoustics and Content Understanding)