Skip to content

Latest commit

 

History

History
9 lines (8 loc) · 668 Bytes

README.md

File metadata and controls

9 lines (8 loc) · 668 Bytes

Collection of Deep Reinforcement Learning scripts (as short as possible) on simple gym environments.

Why this repo exists:

  • For learning purposes.
  • Because most implementations around the web have the algorithms wrapped on triple wrapped methods/classes, making it hard to read.
  • Because people that want to learn about DRL do not want to get their eyes twisted by Atari Wrappers.
  • From https://arxiv.org/pdf/1709.06560.pdf , performances vary highly across different implementations. So I wanted to create a small repo where every script works out of the box, on simple environments.
  • The focus is: Simple to read, Simple to work.
  • Standardize experiences.