朱子云：

所谓致知在格物者，言欲致吾之知，在即物而穷其理也。盖人心之灵，莫不有知，而天下之物，莫不有理。惟于理有未穷，故其知有不尽也。是以大学始教，必使学者即凡天下之物，莫不因其已知之理而益穷之，以求至乎其极。至于用力之久，而一时豁然贯通焉，则众物之表里精粗无不到，而吾心之全体大用无不明矣。

📐📏

本代码库通过 sklearn 标准机器学习库以及自己编写的类两种方式，实现了基本的机器学习算法。

• Common Machine Learning Part: 通过更改主函数中的 use_sklearn flag 即可切换；

• Deep Learning Part: use_sklearn, use_keras, use_torch以及 Self-implement 四种实现方式；

• Applications Part: RL + NLP + CV

RL in Robotics

Machine Learning 格物志

1. Single Linear Regression

2. Multiple Linear Regression

3. Logistic Regression

4. KNN

5. Support Vector Machine

6. Naive Bayes

7. Decision Tree

8. Random Forest

9. Feedforward Neural Network

10. Convolutional Neural Network

11. LSTM

12. PCA

13. K-Means

14. Boosting

1. Value Based Methods: Q-learning(Tabular), DQN

2. Policy Based Methods: Vanilla Policy Gradient, TRPO, PPO

3. Actor-Critic Structure: AC, A2C, A3C

4. Deep Deterministic Policy Gradient: DDPG, DDPG C++ (Undone), TD3

5. Soft Actor-Critic

1. GAN

2. Resnet: Pytorch version, libtorch C++ version

1. Transformer

2. BERT