Hands on experience gives a clear understanding of the concepts read. Implementation gives a different and better view of the theoretical knowledge. The errors that we encounter in the process helps learn a lot of things which lectures and books don't teach!
This repository has all the implementations of all the concepts and research papers read.
Each folder has a saperate Readme file where summary of the implemetations are given.
- Multiarmed Bandits
- Tabular RL
- Monte Carlo Methods
- TD learning Methods
- DQN*
- Policy based Mehods**
*There are variants to dqn algorithm which are implemented here
**There are so many policy gradient based algorithms which are implemented here