# grpo

**Repository Path**: bode135/grpo

## Basic Information

- **Project Name**: grpo
- **Description**: deepseek的grpo, 用于gym的carpole环境测试
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 1
- **Created**: 2025-02-08
- **Last Updated**: 2025-07-25

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

视频课程:https://www.bilibili.com/video/BV1X94y1Y7hS

环境信息:

python==3.9

pytorch==1.12.1(cpu)

gym==0.26.2

pettingzoo==1.23.1