3 citations · 3 across the 2 of their papers we have counts for
3 papers
cs.CL2026
The Thinking Leakage in Reinforcement Learning for LLMs
Wenxuan Zhu, Shuming Liu, Bang An +4
Hybrid reasoning models such as the Qwen3 series switch between a THINK mode and a NO-THINK mode through a few chat-template tokens. A popular recipe trains such models with reinfo…
cs.LG2022
Causal Deep Reinforcement Learning Using Observational Data
Wenxuan Zhu, Chao Yu, Qiang Zhang
Deep reinforcement learning (DRL) requires the collection of interventional data, which is sometimes expensive and even unethical in the real world, such as in the autonomous drivi…
cs.HC2018★ 3 cited
Learning Shaping Strategies in Human-in-the-loop Interactive Reinforcement Learning
Chao Yu, Tianpei Yang, Wenxuan Zhu +2
Providing reinforcement learning agents with informationally rich human knowledge can dramatically improve various aspects of learning. Prior work has developed different kinds of…