Date of Publication :30th September 2020

Abstract: Artificial Intelligence (AI) agents should have a precise representation of their surroundings and should be able to retain information based on their past experiences and from sensory inputs. It is done by developing smart self-learning agents using various Deep Reinforcement Learning algorithms such as Q-learning (DQN) and SARSA learning (DSN). These algorithms have helped game developers in removing the monotonous nature of games helping in the augmentation of the gaming industry. Intelligent agents can also be used in game development as these agents inhibit human-like behaviour which can help with the game balancing and assessment, almost identical to the performance of game developers. First Person Shooter (FPS) games have seen a significant gain in popularity due to increased difficulty and lack of predictability. This paper is an attempt in doing the same by reviewing various existing works in this field and some of the popular techniques of developing intelligent Agents.

Reference :