Application of Deep Reinforcement Learning to NS-SHAFT Game Signal Control.

Reinforcement learning (RL) with both exploration and exploit abilities is applied to games to demonstrate that it can surpass human performance. This paper mainly applies Deep Q-Network (DQN), which combines reinforcement learning and deep learning to the real-time action response of NS-SHAFT game with Cheat Engine as the API of game information autonomously. Based on a personal computer, we build an experimental learning environment that automatically captures the NS-SHAFT's frame, which is provided to DQN to decide the action of moving left, moving right, or stay in same location, survey different parameters: such as the sample frequency, different reward function, and batch size, etc. The experiment found that the relevant parameter settings have a certain degree of influence on the DQN learning effect. Moreover, we use Cheat Engine as the API of NS-SHAFT game information to locate the relevant values in the NS-SHAFT game, and then read the relevant values to achieve the operation of the overall experimental platform and the calculation of Reward. Accordingly, we successfully establish an instant learning environment and instant game training for the NS-SHAFT game.