Reinforcement Learning with Dual-Observation for General Video Game Playing

TL;DR

This paper introduces a dual-observation reinforcement learning approach that enhances generalization in unseen video game levels by using encoded local and global observations, tested on competition games.

Contribution

It proposes a novel dual-observation input method for reinforcement learning, improving generalization across different game levels in video game playing.

Findings

Dual-observation method outperforms single-input approaches.

Ablation studies confirm the effectiveness of local and global encoded observations.

Method demonstrates strong performance on 2020 competition games.

Abstract

Reinforcement learning algorithms have performed well in playing challenging board and video games. More and more studies focus on improving the generalisation ability of reinforcement learning algorithms. The General Video Game AI Learning Competition aims to develop agents capable of learning to play different game levels that were unseen during training. This paper summarises the five years' General Video Game AI Learning Competition editions. At each edition, three new games were designed. The training and test levels were designed separately in the first three editions. Since 2020, three test levels of each game were generated by perturbing or combining two training levels. Then, we present a novel reinforcement learning technique with dual-observation for general video game playing, assuming that it is more likely to observe similar local information in different levels rather than global information. Instead of directly inputting a single, raw pixel-based screenshot of the current game screen, our proposed general technique takes the encoded, transformed global and local observations of the game screen as two simultaneous inputs, aiming at learning local information for playing new levels. Our proposed technique is implemented with three state-of-the-art reinforcement learning algorithms and tested on the game set of the 2020 General Video Game AI Learning Competition. Ablation studies show the outstanding performance of using encoded, transformed global and local observations as input.