Qinbo Bai, Mridul Agarwal, Vaneet Aggarwal. Joint Optimization of Concave Scalarized Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm. J. Artif. Intell. Res. (JAIR), 74:1565-1597, 2022. [doi]
@article{BaiAA22, title = {Joint Optimization of Concave Scalarized Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm}, author = {Qinbo Bai and Mridul Agarwal and Vaneet Aggarwal}, year = {2022}, doi = {10.1613/jair.1.13981}, url = {https://doi.org/10.1613/jair.1.13981}, researchr = {https://researchr.org/publication/BaiAA22}, cites = {0}, citedby = {0}, journal = {J. Artif. Intell. Res. (JAIR)}, volume = {74}, pages = {1565-1597}, }