[go: up one dir, main page]

Follow
Qinghua Liu
Qinghua Liu
OpenAI
Verified email at openai.com - Homepage
Title
Cited by
Cited by
Year
Tackling the objective inconsistency problem in heterogeneous federated optimization
J Wang, Q Liu, H Liang, G Joshi, HV Poor
Advances in Neural Information Processing Systems, 2020, 2020
21912020
Bellman Eluder dimension: New rich classes of RL problems, and sample-efficient algorithms
C Jin, Q Liu, S Miryoosefi
Advances in Neural Information Processing Systems, 2021, 2021
3302021
A Sharp Analysis of Model-based Reinforcement Learning with Self-play
Q Liu, T Yu, Y Bai, C Jin
International Conference on Machine Learning, 7001-7010, 2021
1832021
V-learning—a simple, efficient, decentralized algorithm for multiagent reinforcement learning
C Jin, Q Liu, Y Wang, T Yu
Mathematics of Operations Research 49 (4), 2295-2322, 2024
179*2024
When is partially observable reinforcement learning not scary?
Q Liu, A Chung, C Szepesvári, C Jin
Conference on Learning Theory, 5175-5220, 2022
1632022
Linearized admm for nonconvex nonsmooth optimization with convergence analysis
Q Liu, X Shen, Y Gu
arXiv preprint arXiv:1705.02502, 2017
1622017
A novel framework for the analysis and design of heterogeneous federated learning
J Wang, Q Liu, H Liang, G Joshi, HV Poor
IEEE Transactions on Signal Processing 69, 5234-5249, 2021
1592021
Is rlhf more difficult than standard rl? a theoretical perspective
Y Wang, Q Liu, C Jin
Advances in Neural Information Processing Systems 36, 76006-76032, 2023
1222023
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
C Jin, SM Kakade, A Krishnamurthy, Q Liu
Advances in Neural Information Processing Systems, 2020, 2020
1142020
The power of exploiter: Provable multi-agent rl in large state spaces
C Jin, Q Liu, T Yu
International Conference on Machine Learning, 10251-10279, 2022
812022
Optimistic mle: A generic model-based algorithm for partially observable sequential decision making
Q Liu, P Netrapalli, C Szepesvari, C Jin
Proceedings of the 55th Annual ACM Symposium on Theory of Computing, 363-376, 2023
662023
Sample-efficient reinforcement learning of partially observable markov games
Q Liu, C Szepesvári, C Jin
Advances in Neural Information Processing Systems 35, 18296-18308, 2022
602022
Breaking the curse of multiagency: Provably efficient decentralized multi-agent rl with function approximation
Y Wang, Q Liu, Y Bai, C Jin
Conference on Learning Theory, 2023, 2023
542023
Policy optimization for markov games: Unified framework and faster convergence
R Zhang, Q Liu, H Wang, C Xiong, N Li, Y Bai
Advances in Neural Information Processing Systems 35, 21886-21899, 2022
422022
Is best-of-n the best of them? coverage, scaling, and optimality in inference-time alignment
A Huang, A Block, Q Liu, N Jiang, A Krishnamurthy, DJ Foster
arXiv preprint arXiv:2503.21878, 2025
332025
Learning markov games with adversarial opponents: Efficient algorithms and fundamental limits
Q Liu, Y Wang, C Jin
International Conference on Machine Learning, 14036-14053, 2022
292022
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
Q Liu, G Weisz, A György, C Jin, C Szepesvári
Thirty-seventh Conference on Neural Information Processing Systems, 2023
192023
Provable rich observation reinforcement learning with combinatorial latent states
D Misra, Q Liu, C Jin, J Langford
International Conference on Learning Representations, 2021
112021
Rigorous restricted isometry property of low-dimensional subspaces
G Li, Q Liu, Y Gu
Applied and Computational Harmonic Analysis 49 (2), 608-635, 2018
92018
Learning to achieve goals with belief state transformers
ES Hu, K Ahn, Q Liu, H Xu, M Tomar, A Langford, D Jayaraman, A Lamb, ...
arXiv e-prints, arXiv: 2410.23506, 2024
82024
The system can't perform the operation now. Try again later.
Articles 1–20