Hongru/RL_SAC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor code structure for improved readability and maintainability

Browse Source
This commit is contained in:
Hongru
2026-04-04 20:10:26 +08:00
parent 2513ee91ca
commit 427fbc8c2b
6 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitignore
+5
View File
@@ -40,3 +40,8 @@ events.out.tfevents.*
# OS # OS
.DS_Store .DS_Store
Thumbs.db Thumbs.db
# 排除掉几个需要输出的图片
!comparison_curve.png
!sac_learning_curve.png
!ppo_learning_curve.png
comparison_curve.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 689 KiB

configs/pendulum_config.yaml → configs/sac_pendulum_config.yaml
+1 -1
View File
@@ -16,4 +16,4 @@ batch_size: 256 # 每次梯度更新抽样的 batch 大小
# --- 训练循环控制 --- # --- 训练循环控制 ---
max_episodes: 200 # 总共训练多少个 episode max_episodes: 200 # 总共训练多少个 episode
max_steps: 200 # 每 episode 最多步数 (Pendulum-v1 默认 200 步截断) max_steps: 200 # 每 episode 最多步数 (Pendulum-v1 默认 200 步截断)
start_steps: 10000 # 纯随机动作探索的步数 start_steps: 3000 # 纯随机动作探索的步数
ppo_learning_curve.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 496 KiB

sac_learning_curve.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 327 KiB

train.py
+1 -1
View File
@@ -35,7 +35,7 @@ def load_config(path: str) -> dict:
ROOT = os.path.dirname(os.path.abspath(__file__)) ROOT = os.path.dirname(os.path.abspath(__file__))
SAC_CFG_PATH = os.path.join(ROOT, "configs", "pendulum_config.yaml") SAC_CFG_PATH = os.path.join(ROOT, "configs", "sac_pendulum_config.yaml")
PPO_CFG_PATH = os.path.join(ROOT, "configs", "ppo_pendulum_config.yaml") PPO_CFG_PATH = os.path.join(ROOT, "configs", "ppo_pendulum_config.yaml")