@article{balancedqlearningcombiningtheinfluence, title = {Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets}, author = {Thommen George Karimpanal and Hung Le and Majid Abdolshah and Santu Rana and Sunil Gupta and Truyen Tran and Svetha Venkatesh}, year = {2021}, eprint = {2111.02787}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2111.02787v1}, }