| Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning F Feng, R Wang, W Yin, SS Du, L Yang Advances in Neural Information Processing Systems 33, 2020 | 29* | 2020 |
| Provably Correct Optimization and Exploration with Non-linear Policies F Feng, W Yin, A Agarwal, L Yang arXiv preprint arXiv:2103.11559, 2021 | 18 | 2021 |
| A2BCD: Asynchronous acceleration with optimal complexity R Hannah, F Feng, W Yin International Conference on Learning Representations, 2018 | 15 | 2018 |
| A2BCD: An asynchronous accelerated block coordinate descent algorithm with optimal complexity R Hannah, F Feng, W Yin arXiv preprint arXiv:1803.05578, 2018 | 12 | 2018 |
| Acceleration of SVRG and Katyusha X by Inexact Preconditioning Y Liu, F Feng, W Yin http://proceedings.mlr.press/v97/liu19a.html, 2019 | 8 | 2019 |
| Does knowledge transfer always help to learn a better policy F Feng, W Yin, LF Yang arXiv preprint arXiv:1912.02986, 2019 | 7 | 2019 |
| AsyncQVI: Asynchronous-Parallel Q-Value Iteration for Discounted Markov Decision Processes with Near-Optimal Sample Complexity Y Zeng, F Feng, W Yin International Conference on Artificial Intelligence and Statistics, 713-723, 2020 | 5* | 2020 |
| How Does an Approximate Model Help in Reinforcement Learning? F Feng, W Yin, LF Yang arXiv preprint arXiv:1912.02986, 2019 | 5 | 2019 |
| Efficient Reinforcement Learning in Various Environments: from the Idealized to the Realistic F Feng University of California, Los Angeles, 2021 | | 2021 |
| ARock-SOCP: An asynchronous parallel algorithm for second-order cone programming W Ba, F Feng, W Yin | | 2016 |
| A2BCD: AsynchronousAccelerationwithOptimalComplexity R Hannah, F Feng, W Yin | | |
Wotao YinDAMO Academy, Alibaba Group USVerified email at alibaba-inc.com
