This is the repository for the 2023 Seasons of Code Project "Hands on Reinforcement Learning".
- Ashwin Abraham
- Jujhaar Singh
- Prerak Contractor
- Sankalp Bhamare
The assignments for each week will be posted here. You must make a pull request with your solutions, and the best solution will be accepted.
Your solution should ideally be in the form of a Jupyter Notebook. Some assignments will build off each other to form the project.
| Week | Reading | Assignment |
|---|---|---|
| Week 1 | Dynamic Programming (S&B Chapter 4) Introduction to Deep RL (Grokking Chapter 1) |
Link |
| Week 2 | Monte Carlo Methods (S&B Chapter 5) | Link |
| Week 3 | Temporal Difference Learning and Q Learning (S&B Chapter 6) Introduction to Value Based Deep RL (Grokking Chapter 8) |
|
| Week 4 | Eligibility Traces (S&B Chapter 7) | |
| Week 5 | Tabular Methods(S&B Chapter 8) Deep Q Learning Networks (Grokking Chapters 9, 10) |
|
| Week 6 | Approximate Solution Methods (S&B Chapters 9, 11) | |
| Week 7 | Applications (S&B Chapter 14) Advanced Methods (Grokking Chapters 11, 12) |
- Notes on Reinforcement Learning
- Sutton and Barto
- Grokking Deep Reinforcement Learning
- Slides by David Silver
- CS 747 Slides by Prof Shivaraman
- The OpenAI Gym
- A Deep RL course
A ton of resources have been linked here but we'll be mainly following the first three, and will utilize the rest as and when required. The notes will be updated regularly with each week's material.