AAAI-20 is the thirty-fourth AAAI Conference on Artificial Intelligence, one of the world's most prominent international conferences on the subject. Held this year in New York from February 7-12, AAAI promotes theoretical and applied AI research as well as intellectual interchange among researchers and practitioners. As with previous years, this year's AAAI included a Student Abstract Program that allows undergraduate, Master's, and PhD students to submit short, extended abstracts. Brown CS undergraduate Nishanth Kumar's abstract was one of the few chosen from numerous submissions, and it was included in the conference proceedings.
Nishanth is an Undergraduate Research Assistant in Brown CS Professor Stefanie Tellex's Humans 2 Robots Lab whose interests include robotics, artificial intelligence, and using hardware and software to create truly useful products. Primarily advised by Stefanie, his other advisors include Professor George Konidaris and Michael Littman of Brown CS.
"My work for the conference," Nishanth explains, "was about discerning relevance within large world-models. AI agents, such as intelligent robots, possess models of the world that they use to perform specific tasks. It is common practice for programmers to hand-design models to only contain relevant information. However, generally-intelligent agents must automatically discern this relevance for themselves based on the particular task they are given. My work proposes an algorithm to do this, which will hopefully help AI agents solve difficult, large-problems like Minecraft in the future."
For more information, click the link that follows to contact Brown CS Communication Outreach Specialist Jesse C. Polhemus.