Hao Sun, Lei Han, Rui Yang 0010, Xiaoteng Ma, Jian Guo, Bolei Zhou. Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping. 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{SunH0MGZ22, title = {Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping}, author = {Hao Sun and Lei Han and Rui Yang 0010 and Xiaoteng Ma and Jian Guo and Bolei Zhou}, year = {2022}, url = {http://papers.nips.cc/paper_files/paper/2022/hash/f600d1a3f6a63f782680031f3ce241a7-Abstract-Conference.html}, researchr = {https://researchr.org/publication/SunH0MGZ22}, 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}, }