docs: 添加强化学习项目报告及相关文件

Browse Source

添加完整的强化学习个人项目报告，包括PDF文档、LaTeX源文件、训练曲线图、TensorBoard日志以及改进的训练脚本。报告详细记录了从零实现PPO算法解决CarRacing-v3环境的过程，包含算法设计、网络架构、超参数配置和实验结果分析。

...

This commit is contained in:

刘航宇

2026-04-30 22:59:14 +08:00

parent b32490ae03

commit 6b929e9790

12 changed files with 3209 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

强化学习个人项目报告/CW1_1234560.pdf

BIN

Binary file not shown.