Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/rennamahcus/hands-on-rl
Hands-on-RL exploration and development.
https://github.com/rennamahcus/hands-on-rl
artificial-intelligence dynamic-programming machine-learning markov-decision-processes matplotlib numpy pandas pygame pygame-ce python reinforcement-learning scikit-learn
Last synced: about 2 months ago
JSON representation
Hands-on-RL exploration and development.
- Host: GitHub
- URL: https://github.com/rennamahcus/hands-on-rl
- Owner: rennaMAhcuS
- License: other
- Created: 2024-06-05T09:41:23.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2024-07-30T12:09:01.000Z (6 months ago)
- Last Synced: 2024-07-30T15:16:04.656Z (6 months ago)
- Topics: artificial-intelligence, dynamic-programming, machine-learning, markov-decision-processes, matplotlib, numpy, pandas, pygame, pygame-ce, python, reinforcement-learning, scikit-learn
- Language: Python
- Homepage:
- Size: 29.4 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# Hands on RL
> [!NOTE]
>
> To solve the questions in the Weeks (If you are interested 😊), check out the Questions folder in the Weeks.
> Check out the [**Course Info**](CourseInfo.md) file for more details!
>
> Note: The books that have copyrights aren't being uploaded here.
> The books in the Resources/Books/ directory are downloaded from the sources listed in the
> 'Books and Resources' section.
>
> If you want to learn from this repository(❤️), follow the README files to stay organized and on track.
> ## License
> This work is licensed under the
> [**Creative Commons Attribution-ShareAlike 4.0 International License**](https://creativecommons.org/licenses/by-sa/4.0/legalcode).
>
> Refer [**this**](https://github.com/rennaMAhcuS/Hands-on-RL-Source) for more info!
## [Books and Resources](Resources/Books)
- [**Grokking RL**](https://www.google.co.in/books/edition/Grokking_Deep_Reinforcement_Learning/-7YCEAAAQBAJ):
I didn't find an official resource 😢...
- [**Sutton and Barto**](https://www.google.co.in/books/edition/Reinforcement_Learning_second_edition/5s-MEAAAQBAJ):
This book can be downloaded from:
- [**Carnegie Mellon University's website**](https://www.andrew.cmu.edu/course/10-703/textbook/BartoSutton.pdf)
- [**Stanford University's website**](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf)
- [**Direct PDF**](Resources/Books/Sutton_and_Barto.pdf)
- [**Thompson Sampling**](https://www.google.co.in/books/edition/A_Tutorial_on_Thompson_Sampling/nXx6uQEACAAJ):
This resource can be obtained from:
- [**Stanford University's website**](https://web.stanford.edu/~bvr/pubs/TS_Tutorial.pdf)
- [**Direct PDF**](Resources/Books/TS_Tutorial.pdf)
## Repository Structure
```text
.
├── Resources/
│ └── Books/
├── Week1/
│ ├── Assignment/
│ ├── {Solved Files} # Files related to solved questions
│ └── README.md
├── Week2/
│ ├── Assignment/
│ ├── {Solved Files} # Files related to solved questions
│ └── README.md
.
. (Continue similarly for other weeks)
.
├── .gitignore
├── CourseInfo.md
└── README.md
```
## [Week 1](Week1)
This week covers the basic topics of **`python`** required for **Machine Learning** and **Reinforcement Learning**.
The basics of **Reinforcement Learning** are also covered in the books **Grokking RL** and **Sutton and Barto**.
## [Week 2](Week2)
This week covers the basics of **Reinforcement Learning**, mainly covered from **Grokking RL**.
It also has an assignment to cover the basics of writing a game in **`python`** using the **`pygame`** module.
## [Week 3](Week3)
This week covers the algorithms to deal with **Prediction and Control problems**.
## [Week 4](Week4)
This week covers the implementation of the Multi-armed bandit problem implemented in **`python`**.
## [Week 5](Week5)
This week covers **Temporal Difference Learning**, **Q Learning** and **Eligibility Traces** along with a simple game
and using **Q-learning** to **"solve"** the environment.
## [Week 6](Week6)
We have reached the ending!
We will be implementing [**this paper**](Week6/thesis.pdf) to create a Chess Engine based on Deep RL.
---
# Happy Learning 🥰!
---
> [!TIP]
>
> There were some dead weeks also in between in my SoC.
> Considering those also would make this an ~8-Week course.
> I have removed all the inactive weeks from this repository to streamline it for convenient learning.