| Elf: An extensive, lightweight and flexible research platform for real-time strategy games Y Tian, Q Gong, W Shang, Y Wu, CL Zitnick arXiv preprint arXiv:1707.01067, 2017 | 110 | 2017 |
| Elf opengo: An analysis and open reimplementation of alphazero Y Tian, J Ma, Q Gong, S Sengupta, Z Chen, J Pinkerton, L Zitnick International Conference on Machine Learning, 6244-6253, 2019 | 51 | 2019 |
| Hierarchical decision making by generating and following natural language instructions H Hu, D Yarats, Q Gong, Y Tian, M Lewis arXiv preprint arXiv:1906.00744, 2019 | 20 | 2019 |
| Luck matters: Understanding training dynamics of deep relu networks Y Tian, T Jiang, Q Gong, A Morcos arXiv preprint arXiv:1905.13405, 2019 | 14 | 2019 |
| Polygames: Improved zero learning T Cazenave, YC Chen, GW Chen, SY Chen, XD Chiu, J Dehos, M Elsa, ... ICGA Journal, 1-13, 2020 | 12 | 2020 |
| Combining deep reinforcement learning and search for imperfect-information games N Brown, A Bakhtin, A Lerer, Q Gong arXiv preprint arXiv:2007.13544, 2020 | 9 | 2020 |
| Facebook Open Sources ELF OpengGo Y Tian, L Zitnick Facebook Research, May, 2018 | 9 | 2018 |
| Elf opengo Y Tian, J Ma, Q Gong, S Sengupta, Z Chen, CL Zitnick | 8 | 2018 |
| Latent forward model for real-time strategy game planning with incomplete information Y Tian, Q Gong | 6 | 2018 |
| Techniques for capturing state information and performing actions for threads in a multi-threaded computing environment Y Tian, Q Gong, WU Yuxin US Patent 10,387,161, 2019 | 4 | 2019 |
| Joint policy search for multi-agent collaboration with imperfect information Y Tian, Q Gong, T Jiang arXiv preprint arXiv:2008.06495, 2020 | 3 | 2020 |
| Simple is better: Training an end-to-end contract bridge bidding agent without human knowledge Q Gong, Y Jiang, Y Tian | 2 | 2019 |
| All Simulations Are Not Equal: Simulation Reweighing for Imperfect Information Games Q Gong, Y Tian | | 2019 |
Yuandong TianResearch Scientist, Facebook AI ResearchVerified email at fb.com
