Dong Ki Kim, Miao Liu 0001, Matthew Riemer, Chuangchuang Sun, Marwa Abdulhai, Golnaz Habibi, Sebastian Lopez-Cot, Gerald Tesauro, Jonathan P. How. A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning. In Marina Meila, Tong Zhang 0001, editors, Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. Volume 139 of Proceedings of Machine Learning Research, pages 5541-5550, PMLR, 2021. [doi]
@inproceedings{Kim0RSAHLTH21,
title = {A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning},
author = {Dong Ki Kim and Miao Liu 0001 and Matthew Riemer and Chuangchuang Sun and Marwa Abdulhai and Golnaz Habibi and Sebastian Lopez-Cot and Gerald Tesauro and Jonathan P. How},
year = {2021},
url = {http://proceedings.mlr.press/v139/kim21g.html},
researchr = {https://researchr.org/publication/Kim0RSAHLTH21},
cites = {0},
citedby = {0},
pages = {5541-5550},
booktitle = {Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event},
editor = {Marina Meila and Tong Zhang 0001},
volume = {139},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}