Michel Deudon, Pierre Cournut, Alexandre Lacoste, Yossiri Adulyasak, Louis-Martin Rousseau. Learning Heuristics for the TSP by Policy Gradient. In Willem Jan van Hoeve, editor, Integration of Constraint Programming, Artificial Intelligence, and Operations Research - 15th International Conference, CPAIOR 2018, Delft, The Netherlands, June 26-29, 2018, Proceedings. Volume 10848 of Lecture Notes in Computer Science, pages 170-181, Springer, 2018. [doi]
@inproceedings{DeudonCLAR18,
title = {Learning Heuristics for the TSP by Policy Gradient},
author = {Michel Deudon and Pierre Cournut and Alexandre Lacoste and Yossiri Adulyasak and Louis-Martin Rousseau},
year = {2018},
doi = {10.1007/978-3-319-93031-2_12},
url = {https://doi.org/10.1007/978-3-319-93031-2_12},
researchr = {https://researchr.org/publication/DeudonCLAR18},
cites = {0},
citedby = {0},
pages = {170-181},
booktitle = {Integration of Constraint Programming, Artificial Intelligence, and Operations Research - 15th International Conference, CPAIOR 2018, Delft, The Netherlands, June 26-29, 2018, Proceedings},
editor = {Willem Jan van Hoeve},
volume = {10848},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-319-93031-2},
}