Report of the 1996 Workshop on Reinforcement Learning Sponsored by the National Science Foundation Preface and Acknowledgements

This document describes the results of a two-day meeting of leading researchers in the area of reinforcement learning (RL). As RL is an interdisciplinary topic, the aim was to bring together researchers from a variety of elds, including machine learning, neural networks, arti cial intelligence, robotics, and operations research. Thirty leading researchers in the eld participated in the workshop, from many di erent universities, government and industrial research laboratories. The goals of the meeting were to (1) understand limitations of current RL systems and de ne 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. 2