Will GPT-4 Run DOOM?
This work explores the potential for LLM-based agents in video games, though it is incremental as it builds on existing LLM capabilities without surpassing traditional methods.
The researchers demonstrated that GPT-4 can play the 1993 game Doom using its reasoning and planning capabilities, achieving passable performance in tasks like manipulating doors and combat without any training.
We show that GPT-4's reasoning and planning capabilities extend to the 1993 first-person shooter Doom. 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.