AI Rank
EN
← 开源
seungeunrho

minimalRL

Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

TutorialsML/AI fundamentalsPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
3.24k
Star
491
Fork
+6
本周
4
贡献者
创建于 2019-04-23 · 更新于 2026-10-15 · 今日第 8045 名
主要开发者
seungeunrhorahulptelrossrho

seungeunrho/minimalRL 排名第 8,045，有 3,240 个星标。

同类别比较

seungeunrho/minimalRL 排名第 8,045，此处有 8 个同类条目；patrickloeber/ml-study-plan 排名第 8,050。

同类别比较
名称排名指标
tirthajyoti/Machine-Learning-with-Python7,991
语言:
Jupyter Notebook
星标数:
3,338
分叉数:
1,828
简介:
Practice and tutorial-style notebooks covering wide variety of machine learning techniques
Sakura-gh/ML-notes8,021
语言:
HTML
星标数:
3,280
分叉数:
886
简介:
notes about machine learning
graykode/nlp-roadmap8,026
星标数:
3,269
分叉数:
513
简介:
ROADMAP(Mind Map) and KEYWORD for students those who have interest in learning NLP
fchollet/keras-resources8,028
星标数:
3,266
分叉数:
862
简介:
Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library
patrickloeber/ml-study-plan8,050
星标数:
3,225
分叉数:
427
简介:
The Ultimate FREE Machine Learning Study Plan
tekaratzas/RustGPT8,069
语言:
Rust
星标数:
3,187
分叉数:
269
简介:
An transformer based LLM. Written completely in Rust
yusugomori/DeepLearning8,071
语言:
Java
星标数:
3,187
分叉数:
1,343
简介:
Deep Learning (Python, C, C++, Java, Scala, Go)
higgsfield/RL-Adventure8,072
语言:
Jupyter Notebook
星标数:
3,186
分叉数:
588
简介:
Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
关键参数与规格
关键参数与规格
参数值
语言Python
类别Tutorials
子类别ML/AI fundamentals
关键词RL
星标数3,240
分叉数491
贡献者4
创建日期2019-04-23
更新日期2026-10-15
1 天星标数0
7 天星标数6
排名8,045
上次排名8,130
排名变化85
7 天星标排名5,027
上次 7 天星标排名5,027
7 天星标排名变化0
总星标排名4,203
上次总星标排名4,200
总星标排名变化-3
国家USA
README 摘录

minimalRL-pytorch Implementations of basic RL algorithms with minimal lines of codes! (PyTorch based) Each algorithm is complete within a single file. Length of each file is up to 100~150 lines of codes. Every algorithm can be trained within 30 seconds, even without GPU. You can just focus on the implementations. DQN (112 lines, including replay memory and target network) 4. DDPG (145 lines, including OU noise and soft target update) 6. No longer support for the previous versions

) Usage

常见问题

记录了多少星标和分叉？

seungeunrho/minimalRL 有 3,240 个星标和 491 个分叉。

仓库排名是多少？

seungeunrho/minimalRL 排名第 8,045。

记录的语言和类别是什么？

seungeunrho/minimalRL 有 3,240 个星标，语言为 Python，类别为 Tutorials。

哪个仓库排名最接近？

seungeunrho/minimalRL 与 patrickloeber/ml-study-plan 比较，后者排名第 8,050，有 3,225 个星标。

README

minimalRL-pytorch

Implementations of basic RL algorithms with minimal lines of codes! (PyTorch based)

  • Each algorithm is complete within a single file.

  • Length of each file is up to 100~150 lines of codes.

  • Every algorithm can be trained within 30 seconds, even without GPU.

  • Envs are fixed to "CartPole-v1". You can just focus on the implementations.

Algorithms

  1. REINFORCE (67 lines)
  2. Vanilla Actor-Critic (98 lines)
  3. DQN (112 lines, including replay memory and target network)
  4. PPO (119 lines, including GAE)
  5. DDPG (145 lines, including OU noise and soft target update)
  6. A3C (129 lines)
  7. ACER (149 lines)
  8. A2C (188 lines)
  9. SAC (171 lines) added!!
  10. PPO-Continuous (161 lines) added!!
  11. Vtrace (137 lines) added!!
  12. Any suggestion ...?

Dependencies

  1. PyTorch
  2. OpenAI GYM ( > 0.26.2 IMPORTANT!! No longer support for the previous versions)

Usage

# Works only with Python 3.
# e.g.
python3 REINFORCE.py
python3 actor_critic.py
python3 dqn.py
python3 ppo.py
python3 ddpg.py
python3 a3c.py
python3 a2c.py
python3 acer.py
python3 sac.py
排名相邻
同类项目