Deep Reinforcement Learning for General Video Game AI
This work addresses the need for benchmarking AI in diverse video games, but it is incremental as it adapts existing methods to a new framework without major innovations.
The paper tackled the problem of applying deep reinforcement learning to the General Video Game AI (GVGAI) framework by interfacing it with OpenAI Gym, and the result showed that widely used deep reinforcement learning algorithms performed variably across games, with an analysis indicating relative game difficulties compared to the Arcade Learning Environment.
The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward model that allows the use of algorithms such as Monte Carlo Tree Search. In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems. Using this interface, we characterize how widely used implementations of several deep reinforcement learning algorithms fare on a number of GVGAI games. We further analyze the results to provide a first indication of the relative difficulty of these games relative to each other, and relative to those in the Arcade Learning Environment under similar conditions.