QDN: An Efficient Value Decomposition Method for Cooperative Multi-agent Deep Reinforcement Learning.
Zaipeng XieYufeng ZhangPengfei ShaoWeiyi ZhaoPublished in: ICTAI (2022)
Keyphrases
- decomposition method
- reinforcement learning
- cooperative multi agent
- decomposition methods
- decomposition algorithm
- tree decomposition
- function approximation
- state space
- learning algorithm
- reinforcement learning algorithms
- markov decision processes
- supervised learning
- logic programming
- data sets
- relational databases
- multi agent
- genetic algorithm
- machine learning
- learning problems
- object oriented
- learning process
- knowledge base
- autonomous learning