← Back to Timeline

Week 1

Foundations of RL & Q-Learning

Understanding MDPs, exploration strategies, and tabular learning methods.

Topics Covered

Teaching Markov Decision Process (MDP)
Understanding Epsilon-greedy and other exploration strategies
Tabular learning methods like Q-Learning
Drawbacks of tabular methods and motivation for deep RL
Setting up a basic RL environment with Gymnasium

Resources

Session Presentation

Week 1 Session Slides

PDF of the presentation from our first session

Introduction to RL and Q-Learning

Introduction to RL and Q-Learning

Watch this playlist till video 6: Q Learning

If yu want a more intuitive understanding of MDPs check these out:

Markov Decision Process

For intuitive understanding of MDPs

Markov Decision Process

For intuitive understanding of MDPs and Solving them using Value Iteration

For mathematical understanding

CS229: MDP and Value/Policy Iteration

A more mathematical video behind the MDPs and RL you'd wanna see.

For the enviornment

Gymnasium Documentation

Official documentation for RL environments

Reference Books

Reference Books

If you like reading and want get an indepth understand of the topic do check these reference books.

Assignment

View Week 1 Assignment Details →