Deep Learning for Video Game Playing

Justesen, Niels; Bontrager, Philip; Togelius, Julian; Risi, Sebastian

doi:10.1109/tg.2019.2896986

Cited by 196 publications

(127 citation statements)

References 97 publications

(163 reference statements)

Supporting

Mentioning

100

Contrasting

Unclassified

Order By: Relevance

“…7 Towards more general AI While AI algorithms have become exceedingly good at playing specific games [33], it is still an unsolved challenge how to make an AI algorithm that can learn to quickly play any game it is given, or how to transfer skills learned in one game to another. This challenge, also known as General Video Game Playing [22], has resulted in the development of the General Video Game AI framework (GVGAI), a flexible framework designed to facilitate the development of general AI through video game playing [60].…”

Section: Merging State and Pixel Informationmentioning

confidence: 99%

From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI

Risi

Preuß

2020

Künstl Intell

Self Cite

View full text Add to dashboard Cite

This paper reviews the field of Game AI, which not only deals with creating agents that can play a certain game, but also with areas as diverse as creating game content automatically, game analytics, or player modelling. While Game AI was for a long time not very well recognized by the larger scientific community, it has established itself as a research area for developing and testing the most advanced forms of AI algorithms and articles covering advances in mastering video games such as StarCraft 2 and Quake III appear in the most prestigious journals. Because of the growth of the field, a single review cannot cover it completely. Therefore, we put a focus on important recent developments, including that advances in Game AI are starting to be extended to areas outside of games, such as robotics or the synthesis of chemicals. In this article, we review the algorithms and methods that have paved the way for these breakthroughs, report on the other important areas of Game AI research, and also point out exciting directions for the future of Game AI.

show abstract

Section: Merging State and Pixel Informationmentioning

confidence: 99%

From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI

Risi

Preuß

2020

Künstl Intell

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to achieve our goal, we started to investigate the literature [1,3,4,7,14,15,17,19,21,22]. Then, we focused our research on artificial agents for video-games (also called "bots").…”

Section: First Yearmentioning

confidence: 99%

Reasoning in Highly Reactive Environments

Pacenza

2019

Electron. Proc. Theor. Comput. Sci.

View full text Add to dashboard Cite

“…Montezumas Revenge is a notable game from this genre as it requires memorization of other rooms that arent immediately available to the agent. Methods used in this space are DQN-PixelCNN, DQN-CTS, and H-DQN [2,9].…”

Section: Arcade Learning Environmentsmentioning

confidence: 99%

“…The main problem that has been the focus of many researchers has been the micromanagement of units in combat scenarios. Methods such as IQL, COMA, Zero Order, and BiCNet have been performed with promising results [9].…”

Section: Real Time Strategymentioning

confidence: 99%

ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning and Snapshot Ensembling

Schulze

2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

ViZDoom is a robust, first-person shooter reinforcement learning environment, characterized by a significant degree of latent state information. In this paper, double-Q learning and prioritized experience replay methods are tested under a certain ViZDoom combat scenario using a competitive deep recurrent Q-network (DRQN) architecture. In addition, an ensembling technique known as snapshot ensembling is employed using a specific annealed learning rate to observe differences in ensembling efficacy under these two methods. Annealed learning rates are important in general to the training of deep neural network models, as they shake up the statusquo and counter a model's tending towards local optima. While both variants show performance exceeding those of built-in AI agents of the game, the known stabilizing effects of double-Q learning are illustrated, and priority experience replay is again validated in its usefulness by showing immediate results early on in agent development, with the caveat that value overestimation is accelerated in this case. In addition, some unique behaviors are observed to develop for priority experience replay (PER) and double-Q (DDQ) variants, and snapshot ensembling of both PER and DDQ proves a valuable method for improving performance of the ViZDoom Marine.

show abstract

Deep Learning for Video Game Playing

Cited by 196 publications

References 97 publications

From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI

From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI

Reasoning in Highly Reactive Environments

ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning and Snapshot Ensembling

Contact Info

Product

Resources

About