High-Level

High Level Projects

2 Difference Projects

ML -> Using machine learning to reproduce the predictions of the previous year's algorithm

RL -> Using reinforcement learning to learn how the pacbot should play the game from scratch

Setup

1. make sure you're using python 3.10 (preferably using a virtual environment for more organized development) because torch-rl isn't compatible with python 3.11 yet
2. pip install gym
3. pip install pygame
4. pip install numpy

(currently optional steps: the code for the model isn't added yet, but will be needed later)

5. install pytorch based on the instructions here: https://pytorch.org/get-started/locally/
6. pip install torchrl
7. pip install tensordict

now you can run the files normally

Resources

PyTorch:

• https://www.learnpytorch.io/

Reinforcement Learning:

• https://www.coursera.org/specializations/reinforcement-learning
• https://www.youtube.com/watch?v=nyjbcRQ-uQ8&list=PLZbbT5o_s2xoWNVdDudn51XM8lOuZ_Njv

OpenAI Gym:

• https://www.gymlibrary.dev/index.html

PyGame

• https://www.pygame.org/docs/