%0 Journal Article %1 journals/apin/YuanYGDL19 %A Yuan, Yinlong %A Yu, Zhu Liang %A Gu, Zhenghui %A Deng, Xiaoyan %A Li, Yuanqing %D 2019 %J Appl. Intell. %K dblp %N 8 %P 2874-2888 %T A novel multi-step reinforcement learning method for solving reward hacking. %U http://dblp.uni-trier.de/db/journals/apin/apin49.html#YuanYGDL19 %V 49

@article{journals/apin/YuanYGDL19, added-at = {2022-02-07T00:00:00.000+0100}, author = {Yuan, Yinlong and Yu, Zhu Liang and Gu, Zhenghui and Deng, Xiaoyan and Li, Yuanqing}, biburl = {https://www.bibsonomy.org/bibtex/2ee45d7715b0465e765c91b292b745e94/dblp}, ee = {https://doi.org/10.1007/s10489-019-01417-4}, interhash = {3c7384ba0c7eb0914959b8d5c8d90606}, intrahash = {ee45d7715b0465e765c91b292b745e94}, journal = {Appl. Intell.}, keywords = {dblp}, number = 8, pages = {2874-2888}, timestamp = {2024-04-09T02:36:48.000+0200}, title = {A novel multi-step reinforcement learning method for solving reward hacking.}, url = {http://dblp.uni-trier.de/db/journals/apin/apin49.html#YuanYGDL19}, volume = 49, year = 2019 }