Reinforcement Learning and Video Games

TL;DR

This paper explores the application of reinforcement learning combined with deep learning techniques to train agents for playing T-rex Runner, demonstrating some methods outperforming human experts and highlighting batch normalization's positive impact.

Contribution

The study introduces reinforcement learning agents for T-rex Runner using deep Q networks and improvements like batch normalization, showing their effectiveness in game playing.

Findings

Some algorithms outperform human experts.

Batch normalization improves reinforcement learning performance.

Results vary across different methods.

Abstract

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.