Diogo Carvalho, Francisco S. Melo, Pedro Santos 0001. A new convergent variant of Q-learning with linear function approximation. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]
@inproceedings{CarvalhoM020,
title = {A new convergent variant of Q-learning with linear function approximation},
author = {Diogo Carvalho and Francisco S. Melo and Pedro Santos 0001},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/e1696007be4eefb81b1a1d39ce48681b-Abstract.html},
researchr = {https://researchr.org/publication/CarvalhoM020},
cites = {0},
citedby = {0},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual},
editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria-Florina Balcan and Hsuan-Tien Lin},
}