Decentralized Control of Quadrotor Swarms with End-to-end Deep Reinforcement Learning.
Sumeet BatraZhehui HuangAleksei PetrenkoTushar KumarArtem MolchanovGaurav S. SukhatmePublished in: CoRL (2021)
Keyphrases
- end to end
- decentralized control
- collective behavior
- reinforcement learning
- markov decision processes
- multiagent systems
- swarm intelligence
- goal oriented
- smart grid
- particle swarm optimization
- social behavior
- congestion control
- grid systems
- multi agent systems
- virtual communities
- robotic systems
- decision makers
- modular robots
- reinforcement learning algorithms
- optimal policy
- dynamic environments
- state space
- real time
- mobile devices
- power system
- exchange information