Reinforcement Learning and Video Games
This is an incremental improvement for AI game-playing, specifically targeting T-rex Runner with hybrid methods.
The study tackled the problem of applying reinforcement learning to video games by combining deep learning with reinforcement learning to train agents for T-rex Runner, resulting in some agents outperforming human experts while others performed poorly.
Reinforcement learning has exceeded human-level performance in game playing AI with deep learning methods according to the experiments from DeepMind on Go and Atari games. Deep learning solves high dimension input problems which stop the development of reinforcement for many years. This study uses both two techniques to create several agents with different algorithms that successfully learn to play T-rex Runner. Deep Q network algorithm and three types of improvements are implemented to train the agent. The results from some of them are far from satisfactory but others are better than human experts. Batch normalization is a method to solve internal covariate shift problems in deep neural network. The positive influence of this on reinforcement learning has also been proved in this study.