Alert button
Picture for Simon S. Du

Simon S. Du

Alert button

Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments

Jan 31, 2023
Runlong Zhou, Zihan Zhang, Simon S. Du

Figure 1 for Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
Figure 2 for Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
Figure 3 for Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
Viaarxiv icon

Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing

Jan 27, 2023
Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon S. Du, Jason D. Lee

Figure 1 for Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
Figure 2 for Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
Viaarxiv icon

Offline congestion games: How feedback type affects data coverage requirement

Oct 24, 2022
Haozhe Jiang, Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon S. Du

Figure 1 for Offline congestion games: How feedback type affects data coverage requirement
Figure 2 for Offline congestion games: How feedback type affects data coverage requirement
Figure 3 for Offline congestion games: How feedback type affects data coverage requirement
Figure 4 for Offline congestion games: How feedback type affects data coverage requirement
Viaarxiv icon

On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness

Oct 19, 2022
Haotian Ye, Xiaoyu Chen, Liwei Wang, Simon S. Du

Viaarxiv icon

Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies

Oct 04, 2022
Rui Yuan, Simon S. Du, Robert M. Gower, Alessandro Lazaric, Lin Xiao

Figure 1 for Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies
Viaarxiv icon

Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games

Oct 04, 2022
Shicong Cen, Yuejie Chi, Simon S. Du, Lin Xiao

Figure 1 for Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
Figure 2 for Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
Viaarxiv icon

Blessing of Class Diversity in Pre-training

Sep 12, 2022
Yulai Zhao, Jianshu Chen, Simon S. Du

Figure 1 for Blessing of Class Diversity in Pre-training
Figure 2 for Blessing of Class Diversity in Pre-training
Figure 3 for Blessing of Class Diversity in Pre-training
Figure 4 for Blessing of Class Diversity in Pre-training
Viaarxiv icon

Denoised MDPs: Learning World Models Better Than the World Itself

Jul 18, 2022
Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian

Figure 1 for Denoised MDPs: Learning World Models Better Than the World Itself
Figure 2 for Denoised MDPs: Learning World Models Better Than the World Itself
Figure 3 for Denoised MDPs: Learning World Models Better Than the World Itself
Figure 4 for Denoised MDPs: Learning World Models Better Than the World Itself
Viaarxiv icon