Marcus’ joint 2011 JAIR paper ‘A Monte-Carlo AIXI Approximation’ has received an Honorable Mention for the 2014 International Joint Conference on Artificial Intelligence and Journal of Artificial Intelligence Research (IJCAI-JAIR) Best Paper Prize.
This Prize is awarded annually to an outstanding paper published in JAIR in the preceding five calendar years. The Prize Committee is comprised of Associate Editors and members of the JAIR Advisory Board. Their decision is based on both the significance of the paper and the quality of presentation.
The Prize Committee provided the following citation:
"This paper investigates the possibility of designing reinforcement learning agents based on a direct approximation of AIXI, a Bayesian notion of optimality in uncertain sequential decision making environments. Although it had been unclear whether AIXI could provide a practical foundation for designing learning agents, this paper demonstrates the first plausible realization of an AIXI agent by exploiting Monte Carlo tree search and context tree weighting algorithms. The paper presents a bold and original perspective on the difficult problem of partially observable reinforcement learning, while demonstrating impressive results on a range of applications."
The prize and honorable mention will be announced at the Association for the Advancement of Artificial Intelligence AAAI-14 opening ceremony during the conference in Quebec City, 29 July 2014.