Picture for Yuejie Chi

Yuejie Chi

The Blessing of Heterogeneity in Federated Q-learning: Linear Speedup and Beyond

May 18, 2023
Jiin Woo, Gauri Joshi, Yuejie Chi

Figure 1 for The Blessing of Heterogeneity in Federated Q-learning: Linear Speedup and Beyond

Figure 2 for The Blessing of Heterogeneity in Federated Q-learning: Linear Speedup and Beyond

Figure 3 for The Blessing of Heterogeneity in Federated Q-learning: Linear Speedup and Beyond

Figure 4 for The Blessing of Heterogeneity in Federated Q-learning: Linear Speedup and Beyond

* Short version at ICML 2023

Access Paper or Ask Questions

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

May 17, 2023
Gen Li, Wenhao Zhan, Jason D. Lee, Yuejie Chi, Yuxin Chen

Access Paper or Ask Questions

Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression

May 17, 2023
Boyue Li, Yuejie Chi

Figure 1 for Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression

Figure 2 for Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression

Figure 3 for Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression

Figure 4 for Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression

Access Paper or Ask Questions

Asynchronous Gradient Play in Zero-Sum Multi-agent Games

Nov 16, 2022
Ruicheng Ao, Shicong Cen, Yuejie Chi

Figure 1 for Asynchronous Gradient Play in Zero-Sum Multi-agent Games

Figure 2 for Asynchronous Gradient Play in Zero-Sum Multi-agent Games

Figure 3 for Asynchronous Gradient Play in Zero-Sum Multi-agent Games

Access Paper or Ask Questions

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

Access Paper or Ask Questions

Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model

Aug 22, 2022
Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen

Access Paper or Ask Questions