@incollection{NIPS1994_916,
title = {An Actor/Critic Algorithm that is Equivalent to Q-Learning},
author = {Robert H. Crites and Andrew G. Barto},
booktitle = {Advances in Neural Information Processing Systems 7},
editor = {G. Tesauro and D. S. Touretzky and T. K. Leen},
pages = {401--408},
year = {1995},
publisher = {MIT Press},
url = {http://papers.nips.cc/paper/916-an-actorcritic-algorithm-that-is-equivalent-to-q-learning.pdf}
}