@inproceedings{NEURIPS2022_39fac857, author = {Cetin, Edoardo and Celiktutan, Oya}, booktitle = {Advances in Neural Information Processing Systems}, editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh}, pages = {8824--8839}, publisher = {Curran Associates, Inc.}, title = {Policy Gradient With Serial Markov Chain Reasoning}, url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/39fac857b4467e3ef4f358186bb07d81-Paper-Conference.pdf}, volume = {35}, year = {2022} }