Paul Wagner. Optimistic policy iteration and natural actor-critic: A unifying view and a non-optimality result. In Christopher J. C. Burges, Léon Bottou, Zoubin Ghahramani, Kilian Q. Weinberger, editors, Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States. pages 1592-1600, 2013. [doi]
@inproceedings{Wagner13-11,
title = {Optimistic policy iteration and natural actor-critic: A unifying view and a non-optimality result},
author = {Paul Wagner},
year = {2013},
url = {http://papers.nips.cc/paper/5188-optimistic-policy-iteration-and-natural-actor-critic-a-unifying-view-and-a-non-optimality-result},
researchr = {https://researchr.org/publication/Wagner13-11},
cites = {0},
citedby = {0},
pages = {1592-1600},
booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States},
editor = {Christopher J. C. Burges and Léon Bottou and Zoubin Ghahramani and Kilian Q. Weinberger},
}