A Survey of Deep Reinforcement Learning in Video Games

12/23/2019
by   Kun Shao, et al.
39

Deep reinforcement learning (DRL) has made great achievements since proposed. Generally, DRL agents receive high-dimensional inputs at each step, and make actions according to deep-neural-network-based policies. This learning mechanism updates the policy to maximize the return with an end-to-end method. In this paper, we survey the progress of DRL methods, including value-based, policy gradient, and model-based algorithms, and compare their main techniques and properties. Besides, DRL plays an important role in game artificial intelligence (AI). We also take a review of the achievements of DRL in various video games, including classical Arcade games, first-person perspective games and multi-agent real-time strategy games, from 2D to 3D, and from single-agent to multi-agent. A large number of video game AIs with DRL have achieved super-human performance, while there are still some challenges in this domain. Therefore, we also discuss some key points when applying DRL methods to this field, including exploration-exploitation, sample efficiency, generalization and transfer, multi-agent learning, imperfect information, and delayed spare rewards, as well as some research directions.

READ FULL TEXT

page 1

page 2

page 7

research
10/09/2021

TiKick: Toward Playing Multi-agent Football Full Games from Single-agent Demonstrations

Deep reinforcement learning (DRL) has achieved super-human performance o...
research
03/14/2018

Learning to Play General Video-Games via an Object Embedding Network

Deep reinforcement learning (DRL) has proven to be an effective tool for...
research
04/22/2022

Deep Reinforcement Learning Using a Low-Dimensional Observation Filter for Visual Complex Video Game Playing

Deep Reinforcement Learning (DRL) has produced great achievements since ...
research
01/24/2023

DeepADMR: A Deep Learning based Anomaly Detection for MANET Routing

We developed DeepADMR, a novel neural anomaly detector for the deep rein...
research
08/11/2023

Learning to Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding

Multi-agent pathfinding (MAPF) is a critical field in many large-scale r...
research
05/21/2021

Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games

In real-time strategy (RTS) game artificial intelligence research, vario...
research
09/14/2021

Exploration in Deep Reinforcement Learning: A Comprehensive Survey

Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Lea...

Please sign up or login with your details

Forgot password? Click here to reset