Intelligent Non-Person Agent to Play a Game
Creating a non-person character (NPC) to play a game is becoming increasingly important. NPCs can be used in quality assurance to test a game before sending the game for certification. Being able to test a game in a way that mimics a human player would allow the test to be more accurate and would help in discovering design and implementation errors resulting in time and cost savings. Recent research work reported in the literature have focused on skill-based games. Techniques such as Q-learning and reinforcement learning are well-suited to create NPCs for skill-based games where the outcome of a skill-based game depends on the NPC strategy. Such techniques cannot be used to generate an NPC to play a slot game since game outcomes are completely determined by a random number generator. In this project, we need to develop a generative NPC. To achieve this goal, we will first conduct a literature survey in order to select the most suitable techniques for developing the generative NPC. Second, the most promising techniques will be tested, and the results analyzed.