Bai, F., Zhang, H., Tao, T., Wu, Z., Wang, Y., & Xu, B. (2023). PiCor: Multi-Task Deep Reinforcement Learning with Policy Correction. Proceedings of the AAAI Conference on Artificial Intelligence, 37(6), 6728-6736. https://doi.org/10.1609/aaai.v37i6.25825