摸鱼王 Hongru
  • Joined on 2025-09-19
Hongru created branch feat/parallel-rollout-fix in Hongru/RL_TRPO 2026-04-02 17:49:11 +08:00
Hongru pushed to feat/parallel-rollout-fix at Hongru/RL_TRPO 2026-04-02 17:49:11 +08:00
428e6f7f81 修复并行采样并完善训练文档
Hongru pushed to main at Hongru/RL_TRPO 2026-04-02 17:06:17 +08:00
771eba8607 重构 PPO/TRPO 训练流程并添加对比绘图
Hongru created branch main in Hongru/RL_TRPO 2026-04-02 10:25:25 +08:00
Hongru pushed to main at Hongru/RL_TRPO 2026-04-02 10:25:25 +08:00
96cd594be9 first commit
Hongru created repository Hongru/RL_TRPO 2026-04-02 10:12:55 +08:00
Hongru pushed to master at Hongru/RL-Study 2026-03-25 15:38:10 +08:00
7f9d7b2ee6 新增 TRPO 算法实现,包括核心数学引擎、智能体、网络结构及训练入口,完善环境交互与数据处理功能
Hongru pushed to master at Hongru/RL-Study 2026-03-19 18:33:30 +08:00
e53486fece 删除 main_cont.py 文件
Hongru pushed to master at Hongru/RL-Study 2026-03-19 18:29:29 +08:00
0cff2adcf3 添加 DDPG、DPAC、Off-PAC 算法实现及连续动作空间训练代码
Hongru pushed to master at Hongru/RL-Study 2026-03-18 17:07:08 +08:00
6b8156eceb 添加 A2C/QAC 算法实现及训练结果
Hongru pushed to master at Hongru/RL-Study 2026-02-28 15:28:03 +08:00
b13e34cc51 提交代码
Hongru pushed to master at Hongru/RL-Study 2026-02-28 00:18:50 +08:00
2537436fb7 提交代码
Hongru pushed to master at Hongru/RL-Study 2026-02-27 21:17:57 +08:00
1f0096be07 提交代码
Hongru pushed to master at Hongru/RL-Study 2026-02-27 18:33:05 +08:00
da76c6a8a0 调整代码结构
Hongru pushed to master at Hongru/RL-Study 2026-02-27 18:26:19 +08:00
bb67a9a56f Initial commit: Add reinforcement learning study materials and grid world code
Hongru created repository Hongru/RL-Study 2026-02-27 18:19:55 +08:00
Hongru pushed to master at Hongru/RL_Engine_Control 2026-02-06 13:00:58 +08:00
96da685582 添加README
Hongru created branch master in Hongru/RL_Engine_Control 2025-12-30 19:10:51 +08:00
Hongru pushed to master at Hongru/RL_Engine_Control 2025-12-30 19:10:51 +08:00
2757c8afd4 Initial commit
Hongru created repository Hongru/RL_Engine_Control 2025-12-30 19:09:35 +08:00