3M-RL: Multi-Resolution, Multi-Agent, Mean-Field Reinforcement Learning for Autonomous UAV Routing.
Weichang WangYongming LiuRayadurgam SrikantLei YingPublished in: IEEE Trans. Intell. Transp. Syst. (2022)
Keyphrases
- reinforcement learning
- multiresolution
- multi agent
- unmanned aerial vehicles
- autonomous learning
- cooperative
- function approximation
- search and rescue
- state space
- path planning
- reinforcement learning algorithms
- model free
- multi agent environments
- markov random field
- machine learning
- learning capabilities
- rl algorithms
- markov decision processes
- temporal difference
- dynamic environments
- temporal difference learning
- hierarchical representation
- learning algorithm
- single agent
- reinforcement learning agents
- direct policy search
- robotic systems
- belief networks
- transfer learning
- routing protocol
- em algorithm
- partially observable markov decision processes
- learning agents
- autonomous agents
- adaptive control
- partially observable
- complex domains
- control algorithm
- action space
- monte carlo
- multiagent systems
- multi agent systems