The NSF Workshop on Reinforcement Learning : Summary and Observations 1

Reinforcement learning (RL) has become one of the most actively studied learning frameworks in the area of intelligent autonomous agents. This article describes the results of a three-day meeting of leading researchers in this area, sponsored by the National Science Foundation (NSF). As RL is an interdisciplinary topic, the workshop brought together researchers from a variety of elds, including machine learning, neu-ral networks, artiicial intelligence, robotics, and operations research. Thirty leading researchers from the U.S., Canada, Europe, and Japan participated in the workshop, from many diierent universities, government and industrial research laboratories. The goals of the meeting were to (1) understand limitations of current RL systems and deene promising directions for further research, (2) clarify the relationships between RL and existing work in engineering elds, such as operations research, and (3) identify potential industrial applications of RL.