A Survey on Population-Based Deep Reinforcement Learning

Many real-world applications can be described as large-scale games of imperfect information, which require extensive prior domain knowledge, especially in competitive or human–AI cooperation settings. Population-based training methods have become a popular solution to learn robust policies without a...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematics (Basel) Ročník 11; číslo 10; s. 2234
Hlavní autoři: Long, Weifan, Hou, Taixian, Wei, Xiaoyi, Yan, Shichao, Zhai, Peng, Zhang, Lihua
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.05.2023
Témata:
Algorithms
Data mining
Decision making
Deep learning
Digital libraries
Equilibrium
Game theory
Logic programming
Machine learning
Mathematics
multi-agent reinforcement learning
Multiagent systems
Policies
population play
reinforcement learning
Robotics
Robustness (mathematics)
self play
Surveys
Training
ISSN:2227-7390, 2227-7390
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Many real-world applications can be described as large-scale games of imperfect information, which require extensive prior domain knowledge, especially in competitive or human–AI cooperation settings. Population-based training methods have become a popular solution to learn robust policies without any prior knowledge, which can generalize to policies of other players or humans. In this survey, we shed light on population-based deep reinforcement learning (PB-DRL) algorithms, their applications, and general frameworks. We introduce several independent subject areas, including naive self-play, fictitious self-play, population-play, evolution-based training methods, and the policy-space response oracle family. These methods provide a variety of approaches to solving multi-agent problems and are useful in designing robust multi-agent reinforcement learning algorithms that can handle complex real-life situations. Finally, we discuss challenges and hot topics in PB-DRL algorithms. We hope that this brief survey can provide guidance and insights for researchers interested in PB-DRL algorithms.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2227-7390
2227-7390
DOI:10.3390/math11102234