Zhan, Wenhao, Cen, Shicong, Huang, Baihe, Chen, Yuxin, Lee, Jason D., and Chi, Yuejie. Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence. Retrieved from https://par.nsf.gov/biblio/10424937. SIAM Journal on Optimization 33.2 Web. doi:10.1137/21M1456789.

Zhan, Wenhao, Cen, Shicong, Huang, Baihe, Chen, Yuxin, Lee, Jason D., & Chi, Yuejie. Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence. SIAM Journal on Optimization, 33 (2). Retrieved from https://par.nsf.gov/biblio/10424937. https://doi.org/10.1137/21M1456789

Zhan, Wenhao, Cen, Shicong, Huang, Baihe, Chen, Yuxin, Lee, Jason D., and Chi, Yuejie. "Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence". SIAM Journal on Optimization 33 (2). Country unknown/Code not available. https://doi.org/10.1137/21M1456789. https://par.nsf.gov/biblio/10424937.

@article{osti_10424937,
place = {Country unknown/Code not available}, title = {Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence}, url = {https://par.nsf.gov/biblio/10424937}, DOI = {10.1137/21M1456789}, abstractNote = {}, journal = {SIAM Journal on Optimization}, volume = {33}, number = {2}, author = {Zhan, Wenhao and Cen, Shicong and Huang, Baihe and Chen, Yuxin and Lee, Jason D. and Chi, Yuejie}, }