Research regarding "deep paper" on Street Fighter often refers to studies using to create AI agents capable of professional-level gameplay. Key findings from AI research in Street Fighter V :

The AI learns complex strategies, including character-specific combos and defensive maneuvers.

For a complete analysis of competitive Street Fighter, practitioners often refer to specialized wikis and community forums.

Researchers have successfully used Double Deep-Q Networks (DDQN) to train AI agents.

In studies, agents trained through self-play achieved winning rates of up to 95-96% against in-game AI.

The ability to analyze opponent behavior, manage space, and adapt to changing situations, often referred to as "footsies".