This repository contains a PyTorch implementation of Monte Carlo policy gradient reinforcement (REINFORCE) for discrete action spaces.

🚧 🛠️👷‍♀️ 🛑 Under construction...

Install the required dependencies using the following command:

pip install -r requirements.txt

You can run the algorithm on any supported Gymnasium environment. For example:

python main.py --env 'LunarLander-v2'

CartPole-v1	MountainCar-v0	Acrobot-v1

LunarLander-v2	Asteroids-v5	Breakout-v5

BeamRider-v5	Centipede-v5	DonkeyKong-v5

Frogger-v5	KungFuMaster-v5	MarioBros-v5

SpaceInvaders-v5	Tetris-v5	Gopher-v5

MsPacman-v5	Pong-v5	Seaquest-v5

Special thanks to Phil Tabor, an excellent teacher! I highly recommend his Youtube channel.