ChengpengLi

Intermediate
@ChengpengLi1003

CoRT. Python

72

Awesome-Long-Chain-of-Thought-Reasoning-with-tools. A curated list of cutting-edge research papers and resources on Long Chain-of-Thought (CoT) Reasoning with Tools.

46

DotaMath.

30

Q-learning. 针对最经典的表格型Q learning算法进行了复现，能够支持gym中大多数的离散动作和状态空间的环境，譬如CliffWalking-v0。

10

RL4CO. A open-sourced codebase for using offline reinforcement learning in combinatorial optimization

2

MCRL. open-sourced code for kdd23

1

gsm8k-ScRel. Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

1

tensorflowbook. for tensorflow book writting

1
8
Apply