Learning Battles in ViZDoom via Deep Reinforcement Learning

被引：0

作者：

Shao, Kun ^{[1
,2
]}

Zhao, Dongbin ^{[1
,2
]}

Li, Nannan ^{[1
,2
]}

Zhu, Yuanheng ^{[1
,2
]}

机构：

[1] Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China

[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China

来源：

PROCEEDINGS OF THE 2018 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG'18) | 2018年

基金：

中国国家自然科学基金;

关键词：

reinforcement learning; deep learning; game AI;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

First-person shooter (FPS) video games play an important role in game artificial intelligence (AI). In this paper, we present an effective deep reinforcement learning (DRL) method to learn battles in ViZDoom. Our approach utilizes the actor-critic with Kronecker-factored trust region (ACKTR), a sample-efficient and computationally inexpensive DRL method. We train our ACKTR agents in two battle scenarios, and compare with the advantage actor-critic (A2C) baseline agent. The experimental results demonstrate that DRL methods successfully teach agents to battle in these scenarios. In addition, the ACKTR agents significantly outperform the A2C agents in terms of all the metrics by a significant margin.

引用

页码：389 / 392

页数：4

共 50 条

[1] Deep Reinforcement Learning in VizDoom via DQN and Actor-Critic Agents
Bakhanova, Maria
Makarov, Ilya
[J]. ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2021, PT I, 2021, 12861 : 138 - 150
[2] Deep Reinforcement Learning with DQN vs. PPO in VizDoom
Zakharenkov, Anton
Makarov, Ilya
[J]. 21ST IEEE INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND INFORMATICS (CINTI), 2021, : 137 - 142
[3] Learning to Walk via Deep Reinforcement Learning
Haarnoja, Tuomas
Ha, Sehoon
Zhou, Aurick
Tan, Jie
Tucker, George
Levine, Sergey
[J]. ROBOTICS: SCIENCE AND SYSTEMS XV, 2019,
[4] Bayesian Deep Reinforcement Learning via Deep Kernel Learning
Junyu Xuan
Jie Lu
Zheng Yan
Guangquan Zhang
[J]. International Journal of Computational Intelligence Systems, 2018, 12 : 164 - 171
[5] Bayesian Deep Reinforcement Learning via Deep Kernel Learning
Xuan, Junyu
Lu, Jie
Yan, Zheng
Zhang, Guangquan
[J]. INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2019, 12 (01) : 164 - 171
[6] Learning to Drive via Apprenticeship Learning and Deep Reinforcement Learning
Huang, Wenhui
Braghin, Francesco
Wang, Zhuo
[J]. 2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019), 2019, : 1536 - 1540
[7] Scaling Tangled Program Graphs to Visual Reinforcement Learning in ViZDoom
Smith, Robert J.
Heywood, Malcolm, I
[J]. GENETIC PROGRAMMING (EUROGP 2018), 2018, 10781 : 135 - 150
[8] Deep sparse representation via deep dictionary learning for reinforcement learning
Tang, Jianhao
Li, Zhenni
Xie, Shengli
Ding, Shuxue
Zheng, Shaolong
Chen, Xueni
[J]. 2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 2398 - 2403
[9] Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning
Xie, Yuansheng
Vosoughi, Soroush
Hassanpour, Saeed
[J]. 2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 5067 - 5074
[10] Learning to Navigate in Human Environments via Deep Reinforcement Learning
Gao, Xingyuan
Sun, Shiying
Zhao, Xiaoguang
Tan, Min
[J]. NEURAL INFORMATION PROCESSING (ICONIP 2019), PT I, 2019, 11953 : 418 - 429

← 1 2 3 4 5 →