Picture for Jiafan He

Jiafan He

Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs

May 15, 2023
Kaixuan Ji, Qingyue Zhao, Jiafan He, Weitong Zhang, Quanquan Gu

* 34 pages

Access Paper or Ask Questions

Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension

May 15, 2023
Yue Wu, Jiafan He, Quanquan Gu

Figure 1 for Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension

Figure 2 for Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension

* 21 pages, 1 table. To appear in UAI 2023

Access Paper or Ask Questions

Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

May 12, 2023
Yifei Min, Jiafan He, Tianhao Wang, Quanquan Gu

Figure 1 for Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

Figure 2 for Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

Figure 3 for Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

* Published at the 40th International Conference on Machine Learning ( ICML 2023 )

Access Paper or Ask Questions

On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

Mar 16, 2023
Weitong Zhang, Jiafan He, Zhiyuan Fan, Quanquan Gu

Figure 1 for On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

Figure 2 for On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

Figure 3 for On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

Figure 4 for On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

* 28 pages, 2 figures, 2 tables

Access Paper or Ask Questions

Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes

Dec 12, 2022
Jiafan He, Heyang Zhao, Dongruo Zhou, Quanquan Gu

Figure 1 for Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes

* 44 pages, 1 table

Access Paper or Ask Questions

A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

Jul 07, 2022
Jiafan He, Tianhao Wang, Yifei Min, Quanquan Gu

Figure 1 for A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

Figure 2 for A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

Figure 3 for A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

* 25 pages, 1 figure, 2 tables

Access Paper or Ask Questions

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

May 13, 2022
Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu

Figure 1 for Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

* 29 pages, 1 table

Access Paper or Ask Questions

Bandit Learning with General Function Classes: Heteroscedastic Noise and Variance-dependent Regret Bounds

Feb 28, 2022
Heyang Zhao, Dongruo Zhou, Jiafan He, Quanquan Gu

Figure 1 for Bandit Learning with General Function Classes: Heteroscedastic Noise and Variance-dependent Regret Bounds

* 33 pages, 1 table

Access Paper or Ask Questions

Learning Stochastic Shortest Path with Linear Function Approximation

Oct 25, 2021
Yifei Min, Jiafan He, Tianhao Wang, Quanquan Gu

Figure 1 for Learning Stochastic Shortest Path with Linear Function Approximation

* 34 pages, 1 figure

Access Paper or Ask Questions