Gaurav Manek, J. Zico Kolter. The Pitfalls of Regularization in Off-Policy TD Learning. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022. 2022. [doi]
@inproceedings{ManekK22, title = {The Pitfalls of Regularization in Off-Policy TD Learning}, author = {Gaurav Manek and J. Zico Kolter}, year = {2022}, url = {http://papers.nips.cc/paper_files/paper/2022/hash/e78457d4a04b8565f1fe5077df13cddb-Abstract-Conference.html}, researchr = {https://researchr.org/publication/ManekK22}, cites = {0}, citedby = {0}, booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, isbn = {9781713871088}, }