← 返回名录条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。 需要更正或删除？通过收录与更正通道提交，24 小时内处理。
S
Shuai Zhen
Reinforcement Learning & LLM
- 公司
- Beijing University of Posts and Telecommunications
- 位置
- Beijing
- Stars
- 16
- 粉丝 / 仓库
- 2
代表作品 / 项目
- STEP-HRL⭐ 8[ACL 2026 Main Conference] Official Implementation of "Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents"
- LLM-RL⭐ 5A minimal viable implementation to achieve GRPO based on veRL and TRL.
- RL-Lab⭐ 3A framework for reproducing PPO, SAC, TD3, DDPG, DQN_Series, A2C, ect. Support both continuous and discrete action spaces, also support automatically plot learning curves.
- Reflex⭐ 0Official Implementation of "Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control"
- Transformer⭐ 0Translation model based on Transformer, using WMT18 dataset