https://github.com/zhaoyingjun/general
Alignment成为GPT类大模型微调的必须环节，深度强化学习是Alignment的核心。本项目是一个支持非gym环境训练、支持可视化配置的深度强化学习应用编程框架，30分钟上手强化学习编程。
https://github.com/zhaoyingjun/general
ddpg deep-reinforcement-learning dqn gui gym ppo tensorflow2
Last synced: 6 months ago
JSON representation
Alignment成为GPT类大模型微调的必须环节，深度强化学习是Alignment的核心。本项目是一个支持非gym环境训练、支持可视化配置的深度强化学习应用编程框架，30分钟上手强化学习编程。
- Host: GitHub
- URL: https://github.com/zhaoyingjun/general
- Owner: zhaoyingjun
- License: mit
- Created: 2020-01-31T12:34:38.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2023-03-25T00:18:12.000Z (over 2 years ago)
- Last Synced: 2025-03-27T07:35:53.319Z (7 months ago)
- Topics: ddpg, deep-reinforcement-learning, dqn, gui, gym, ppo, tensorflow2
- Language: Python
- Homepage:
- Size: 106 KB
- Stars: 72
- Watchers: 9
- Forks: 18
- Open Issues: 2