Static Analysis for Automated Identification of Valid Game Actions During Exploration

Automated exploration has many important applications for testing and analysis of games. Techniques for automated exploration require the capability of identifying the set of available user actions at a given game state, then performing the action selected by the exploration logic. This has been traditionally supported by having the game developer provide an API for this purpose or randomly guessing inputs. In this paper we develop a program analysis based technique for performing an automated analysis of the input-handling logic of the game code, then using this information to provide the set of player actions available at a game state (as well as the device inputs that should be simulated to perform a chosen action). We focus on developing such a technique for games built with the Unity game engine. We implemented an automatic exploration tool based on our technique and evaluated its state exploration performance for six open-source Unity games. We found that our approach is competitive with manually specified actions and is fast enough to play the games in real time.