Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems.
Guannan QuAdam WiermanNa LiPublished in: L4DC (2020)
Keyphrases
- reinforcement learning
- multi agent
- optimal policy
- reinforcement learning agents
- complex systems
- intelligent systems
- learning algorithm
- state space
- distributed systems
- multimedia
- markov decision processes
- control policies
- decentralized control
- machine learning
- dynamic programming
- expert systems
- multiple agents
- reinforcement learning algorithms
- action space
- policy search
- multi agent environments