Serendipity/rl-atari
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 改进DQN训练稳定性和性能

Browse Source 
- 将奖励裁剪替换为奖励缩放，保留奖励大小信号
- 添加学习率调度器，支持warmup和步进衰减
- 增加经验回放缓冲区大小至200,000
- 默认启用Dueling DQN架构
- 优化代码格式和参数传递
- 添加更多训练中间模型保存点
This commit is contained in:
刘航宇
2026-05-02 02:02:17 +08:00
parent 1c1cccd3f6
commit faf0d5ea42
12 changed files with 122 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files