This repository provides implementations for the algorithms presented in the Reinforcement Learning: An Introduction (2nd Edition) and serve as a learning exercise.
The algorithms are written in Python 3 and use environments from Open AI Gym, together with some custom environments.
The repository is organized as follows:
- The library module contains all the environments and algorithms needed for experimentation
- the environments module contains the testing environments
- the td_learning module contains all the algorithms related to temporal difference learning
- The playgrounds module contains jupyter notebooks with experiments on each topic