Will GPT-4 Run <i>DOOM</i>?

We show that GPT-4’s reasoning and planning capabilities extend to the 1993 first-person shooter <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Doom</i>. This large language model (LLM) is able to run and play the game with only a few instructions, plus a textual description–generated by the model itself from screenshots–about the state of the game being observed. We find that GPT-4 can play the game to a passable degree: it is able to manipulate doors, combat enemies, and perform pathing. More complex prompting strategies involving multiple model calls provide better results. While further work is required to enable the LLM to play the game as well as its classical, reinforcement learning-based counterparts, we note that GPT-4 required no training, leaning instead on its own reasoning and observational capabilities. We hope our work pushes the boundaries on intelligent, LLM-based agents in video games. We conclude by discussing the ethical implications of our work.