Language Breakdown
Lines of code distribution across 4 owned repositories
T-Shaped Developer
T-shapedDeep in Python with broad versatility
Collaboration Network
Global Impact visualization
Repos
6
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
No followers yet.
Top Repositories
A clean and minimal PyTorch implementation of PPO enhanced with the CVor (Control Variates operator). This repository is designed for researchers and beginners to understand how control variates can reduce variance in policy gradient estimates within the PPO framework.
Demo 目的（What problem） 在科研建模与科学大模型下游任务中，不同数据来源（实验条件、仿真参数、设备差异）往往导致模型泛化不稳定。 本 Demo 展示一个训练前 / 训练早期的前置评估模块，用于判断： 给定一个跨来源科研建模任务，是否适合直接采用常规训练（ERM），还是存在明显的高风险泛化问题。 该模块用于辅助工程决策，而非替代训练算法。
Proceedings of ICML 2018
Open Source Impact
Contributions to external projects
No external contributions found.