This project is part of a training I followed on Udemy - https://www.udemy.com/course/deep-q-learning-from-paper-to-code/. It aims at implementing the following paper "Human Level Control Through Deep Reinforcement Learning" available here: https://web.stanford.edu/class/psych209/Readings/MnihEtAlHassibis15NatureControlDeepRL.pdf
The code is written in Pytorch and implements the DQN algorithm applied to the Atari game Pong. We use the OpenAI Gym environment to train the model on the PongNoFrameskip-v4 version.
For training results, please refer to this file Train_DQN_agent.ipynb.