In this article, we’ll explore how Q-learning can be applied to training an agent to play the classic FPS game Doom, through the use of the open-source OpenAI gym wrapper library Vizdoomgym. We’ll guide you through setting up your first agent, and lay the foundations of future work.
An article for TowardsDataScience.
Now with added Pytorch implementations for DQN, Double DQN, Duel DQN, and Double Duel DQN, as part of our follow-up articles on TowardsDataScience.