Yuanhanqing Huang, Jianghai Hu. A Bandit Learning Method for Continuous Games Under Feedback Delays with Residual Pseudo-Gradient Estimate. In 62nd IEEE Conference on Decision and Control, CDC 2023, Singapore, December 13-15, 2023. pages 1207-1212, IEEE, 2023. [doi]
@inproceedings{HuangH23-28, title = {A Bandit Learning Method for Continuous Games Under Feedback Delays with Residual Pseudo-Gradient Estimate}, author = {Yuanhanqing Huang and Jianghai Hu}, year = {2023}, doi = {10.1109/CDC49753.2023.10383332}, url = {https://doi.org/10.1109/CDC49753.2023.10383332}, researchr = {https://researchr.org/publication/HuangH23-28}, cites = {0}, citedby = {0}, pages = {1207-1212}, booktitle = {62nd IEEE Conference on Decision and Control, CDC 2023, Singapore, December 13-15, 2023}, publisher = {IEEE}, isbn = {979-8-3503-0124-3}, }