Picture for Lin F. Yang

Lin F. Yang

A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost

Jan 02, 2021
Minbo Gao, Tianle Xie, Simon S. Du, Lin F. Yang

Figure 1 for A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost

Figure 2 for A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost

Access Paper or Ask Questions

Minimax Sample Complexity for Turn-based Stochastic Game

Nov 29, 2020
Qiwen Cui, Lin F. Yang

* 15 pages

Access Paper or Ask Questions

Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning

Nov 25, 2020
Jingfeng Wu, Vladimir Braverman, Lin F. Yang

Figure 1 for Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning

Access Paper or Ask Questions

Episodic Linear Quadratic Regulators with Low-rank Transitions

Nov 03, 2020
Tianyu Wang, Lin F. Yang

Figure 1 for Episodic Linear Quadratic Regulators with Low-rank Transitions

Figure 2 for Episodic Linear Quadratic Regulators with Low-rank Transitions

Figure 3 for Episodic Linear Quadratic Regulators with Low-rank Transitions

Access Paper or Ask Questions

Random Walk Bandits

Nov 03, 2020
Tianyu Wang, Lin F. Yang, Zizhuo Wang

Figure 1 for Random Walk Bandits

Figure 2 for Random Walk Bandits

Figure 3 for Random Walk Bandits

Access Paper or Ask Questions

Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?

Oct 17, 2020
Qiwen Cui, Lin F. Yang

Figure 1 for Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?

* 30 pages, to appear in NeurIPS2020

Access Paper or Ask Questions

Toward the Fundamental Limits of Imitation Learning

Sep 13, 2020
Nived Rajaraman, Lin F. Yang, Jiantao Jiao, Kannan Ramachandran

Figure 1 for Toward the Fundamental Limits of Imitation Learning

Figure 2 for Toward the Fundamental Limits of Imitation Learning

Figure 3 for Toward the Fundamental Limits of Imitation Learning

Figure 4 for Toward the Fundamental Limits of Imitation Learning

* 45 pages, 3 figures

Access Paper or Ask Questions

Obtaining Adjustable Regularization for Free via Iterate Averaging

Aug 15, 2020
Jingfeng Wu, Vladimir Braverman, Lin F. Yang

Figure 1 for Obtaining Adjustable Regularization for Free via Iterate Averaging

Figure 2 for Obtaining Adjustable Regularization for Free via Iterate Averaging

Figure 3 for Obtaining Adjustable Regularization for Free via Iterate Averaging

Figure 4 for Obtaining Adjustable Regularization for Free via Iterate Averaging

* ICML 2020 camera ready

Access Paper or Ask Questions