Learning Safe Multi-agent Control with Decentralized Neural Barrier Certificates.
Zengyi QinKaiqing ZhangYuxiao ChenJingkai ChenChuchu FanPublished in: ICLR (2021)
Keyphrases
- multi agent
- reinforcement learning
- learning process
- cooperative
- supervised learning
- learning systems
- learning algorithm
- knowledge acquisition
- sensory motor
- neural network
- recurrent networks
- learning agents
- adaptive control
- network architecture
- incremental learning
- learning problems
- markov decision processes
- multiagent systems
- unsupervised learning
- online learning
- prior knowledge
- learning environment
- machine learning