Segui
Qinghua Liu
Qinghua Liu
Microsoft Research
Email verificata su princeton.edu - Home page
Titolo
Citata da
Citata da
Anno
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
13952020
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
2662021
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
1562021
Linearized admm for nonconvex nonsmooth optimization with convergence analysis
Q Liu, X Shen, Y Gu
arXiv preprint arXiv:1705.02502, 2017
1402017
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
125*2024
When is partially observable reinforcement learning not scary?
Q Liu, A Chung, C Szepesvári, C Jin
Conference on Learning Theory, 5175-5220, 2022
1062022
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
902021
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
C Jin, SM Kakade, A Krishnamurthy, Q Liu
Advances in Neural Information Processing Systems, 2020, 2020
822020
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
712022
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
45*2023
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
442023
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
332022
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
312023
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
312022
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
232022
Provable rich observation reinforcement learning with combinatorial latent states
D Misra, Q Liu, C Jin, J Langford
International Conference on Learning Representations, 2021
92021
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
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
82023
A deep reinforcement learning approach for finding non-exploitable strategies in two-player atari games
Z Ding, D Su, Q Liu, C Jin
arXiv preprint arXiv:2207.08894, 2022
32022
Context-lumpable stochastic bandits
CW Lee, Q Liu, Y Abbasi-Yadkori, C Jin, T Lattimore, C Szepesvári
Thirty-seventh Conference on Neural Information Processing Systems, 2023
22023
Il sistema al momento non puň eseguire l'operazione. Riprova piů tardi.
Articoli 1–20