Gen Li 0005, Yuting Wei, Yuejie Chi, Yuxin Chen 0002. Softmax policy gradient methods can take exponential time to converge. Math. Program., 201(1):707-802, 2023. [doi]
@article{0005WC023,
title = {Softmax policy gradient methods can take exponential time to converge},
author = {Gen Li 0005 and Yuting Wei and Yuejie Chi and Yuxin Chen 0002},
year = {2023},
doi = {10.1007/s10107-022-01920-6},
url = {https://doi.org/10.1007/s10107-022-01920-6},
researchr = {https://researchr.org/publication/0005WC023},
cites = {0},
citedby = {0},
journal = {Math. Program.},
volume = {201},
number = {1},
pages = {707-802},
}