Awesome AI for Code
📄
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
Penghui Qi — most-cited papers & profile · AI for Code
← authors
·
overview
Penghui Qi
13
papers ·
62
citations ·
4
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Defeating the Training-Inference Mismatch via FP16
2025 · 34 citations
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
2020 · 28 citations
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
2026
Rethinking the Divergence Regularization in LLM RL
2026
Rethinking the Trust Region in LLM Reinforcement Learning
2026
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
2025
Optimizing Anytime Reasoning via Budget Relative Policy Optimization
2025
Top co-authors
Bowen Ping
· 1
Haonan Wang
· 1
Jiaqi Tang
· 1
Jiarui Yao
· 1
Tianyu Pang
· 1
Xiangxin Zhou
· 1
Topics
cs.LG
Policy Gradient
RLHF & Alignment
Multi-Agent
Game AI
Model-Based RL
cs.AI
cs.CL
Meta-RL
Value-Based