Distilling Reinforcement Learning Tricks for Video Games
This work aims to ease engineering efforts for RL practitioners, particularly in domains like video games, by providing a unified framework to combine proven methods with domain-specific tricks.
The paper tackles the problem of missing engineering tricks in reinforcement learning (RL) by distilling descriptions of tricks from state-of-the-art results and testing them on a standard deep Q-learning agent to improve performance.
Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering steps ("tricks") which may be needed to effectively use RL, such as reward shaping, curriculum learning, and splitting a large task into smaller chunks. Such tricks are common, if not necessary, to achieve state-of-the-art results and win RL competitions. To ease the engineering efforts, we distill descriptions of tricks from state-of-the-art results and study how well these tricks can improve a standard deep Q-learning agent. The long-term goal of this work is to enable combining proven RL methods with domain-specific tricks by providing a unified software framework and accompanying insights in multiple domains.