This week, Professor Michael Littman of Brown CS and his two collaborators on a 1998 paper have won a significant honor at the International Joint Conference on Artificial Intelligence (IJCAI 2021). His paper ("Planning and acting in partially observable stochastic domains"), coauthored with Leslie Pack Kaelbling (formerly of Brown CS, now at MIT) and Brown CS alum Anthony Cassandra (now at RVshare), has won the AIJ Classic Paper Award. The award recognizes outstanding papers published in the journal Artificial Intelligence at least 15 years ago that are exceptional in their significance and impact.
"This is arguably the most well-known paper," write AIJ Editors-in-Chief Patrick Doherty and Sylvie Thiébaux, "for introducing the Partially Observable Markov Decision Process (POMDP) from the field of Operations Research to the field of AI. It summarized the theoretical formalism of POMDPs (as well as novel algorithmic contributions) from the lens of an AI research perspective and did so in a highly accessible and intuitive manner that demystified the technicalities of POMDPs for generations of AI researchers. The introduction and popularization of the POMDP in the field of AI not only contributed to the formal modern perspective of sequential decision-making in AI, but it also had a significant impact on the robotics community, which has adopted the POMDP as a fundamental representational formalism."
Currently co-directing Brown's Humanity-Centered Robotics Initiative, Michael focuses on reinforcement learning, but in addition to his research into POMDP solving, he has worked in in machine learning, game theory, computer networking, computer solving of analogy problems, and other areas.
The original paper is available here.
For more information, click the link that follows to contact Brown CS Communication Outreach Specialist Jesse C. Polhemus.