Ofir Nachum, Mohammad Norouzi, Kelvin Xu, Dale Schuurmans. Bridging the Gap Between Value and Policy Based Reinforcement Learning. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, Roman Garnett, editors, Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA. pages 2772-2782, 2017. [doi]
@inproceedings{NachumNXS17,
title = {Bridging the Gap Between Value and Policy Based Reinforcement Learning},
author = {Ofir Nachum and Mohammad Norouzi and Kelvin Xu and Dale Schuurmans},
year = {2017},
url = {http://papers.nips.cc/paper/6870-bridging-the-gap-between-value-and-policy-based-reinforcement-learning},
researchr = {https://researchr.org/publication/NachumNXS17},
cites = {0},
citedby = {0},
pages = {2772-2782},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA},
editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett},
}