Reinforcement Learning With Dual-Observation for General Video Game Playing

Chengpeng HU, Ziqi WANG, Tianye SHU, Hao TONG, Julian TOGELIUS, Xin YAO, Jialin LIU

Research output: Journal PublicationsJournal Article (refereed)peer-review

Abstract

Reinforcement learning (RL) algorithms have performed well in playing challenging board and video games. More and more studies focus on improving the generalization ability of RL algorithms. The General Video Game AI (GVGAI) Learning Competition aims to develop agents capable of learning to play different game levels that were unseen during training. This article summarizes the five years' GVGAI 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 RL 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 (LOs) 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 RL algorithms and tested on the game set of the 2020 GVGAI Learning Competition. Ablation studies show the outstanding performance of using encoded, transformed global, and LOs as input. © 2018 IEEE.
Original languageEnglish
Pages (from-to)202-216
Number of pages15
JournalIEEE Transactions on Games
Volume15
Issue number2
Early online date1 Apr 2022
DOIs
Publication statusPublished - Jun 2023
Externally publishedYes

Bibliographical note

This work was supported by the Research Institute of TrustworthyAutonomous Systems (RITAS), the Guangdong Provincial Key Laboratory under Grant 2020B121201001, in part by the Program for Guangdong Introducing Innovative and Enterpreneurial Teams under Grant 2017ZT07X386, in part by the Shenzhen Science and Technology Program under Grant KQTD2016112514355531, and in part by the National Natural Science Foundation of China under Grant 61906083.

Keywords

  • Artificial intelligence
  • Atari
  • general video game artificial intelligence (GVGAI)
  • general video game playing (GVGP)
  • reinforcement learning (RL)

Fingerprint

Dive into the research topics of 'Reinforcement Learning With Dual-Observation for General Video Game Playing'. Together they form a unique fingerprint.

Cite this