Skip to content

Latest commit

 

History

History
15 lines (11 loc) · 501 Bytes

File metadata and controls

15 lines (11 loc) · 501 Bytes

Reinforcement Learning Notes

This repository contains small projects that were part of my practice with Reinforcement Learning.

It is divided into 2 modules:

  • classic_algorithms it exposes implementations of classic RL algorithms like:

    • Q-table
    • DQN
    • A2C
      as well as some notes about how these algorithms work.
  • sb3_cheetah_test Experiments with PPO algorithm using Half-Cheetah-v4 gymnasium environment.