Awesome AI Agents
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Yuejie Chi — most-cited papers & profile · AI Agents
← authors
·
overview
Yuejie Chi
51
papers ·
295
citations ·
34
h-index
Yale University · Carnegie Mellon University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Get More With LESS: Synthesizing Recurrence With KV Cache Compression For Efficient LLM Inference
2024 · 84 citations
Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization
2020 · 41 citations
Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
2020 · 29 citations
Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
2021 · 18 citations
Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction
2019 · 11 citations
Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization
2021 · 10 citations
SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression
2022 · 10 citations
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence
2021 · 8 citations
Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
2022 · 8 citations
Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity
2022 · 8 citations
Softmax Policy Gradient Methods Can Take Exponential Time to Converge
2021 · 7 citations
Settling the Sample Complexity of Model-Based Offline Reinforcement Learning
2022 · 7 citations
BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression
2022 · 6 citations
Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction
2020 · 5 citations
Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting
2021 · 5 citations
Top co-authors
Adam Wierman
· 1
Costas Spanos
· 1
Eric Mazumdar
· 1
Laixi Shi
· 1
Ming Jin
· 1
Muning Wen
· 1
Shangding Gu
· 1
Topics
Value-Based
Model-Based RL
Federated Learning
Multi-Agent
Exploration
Communication
Offline RL
Game AI
Policy Gradient
Optimization