A TD3-based multi-agent deep reinforcement learning method in mixed cooperation-competition environment

We explored the problem about function approximation error and complex mission adaptability in multi-agent deep reinforcement learning. This paper proposes a new multi-agent deep reinforcement learning algorithm framework named multi-agent time delayed deep deterministic policy gradient. Our work re...

Celý popis

Podrobná bibliografia

Vydané v:	Neurocomputing (Amsterdam) Ročník 411; s. 206 - 215
Hlavní autori:	Zhang, Fengjiao, Li, Jie, Li, Zhi
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 21.10.2020
Predmet:	Dual-critic MADDPG MATD3 Overestimation error Reinforcement learning Dual-critic MADDPG MATD3 Overestimation error Reinforcement learning
ISSN:	0925-2312, 1872-8286
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!