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.