Multi-UAV Navigation for Partially Observable Communication Coverage by Graph Reinforcement Learning.
Zhenhui YeKe WangYining ChenXiaohong JiangGuanghua SongPublished in: IEEE Trans. Mob. Comput. (2023)
Keyphrases
- partially observable
- reinforcement learning
- state space
- markov decision processes
- partial observability
- decision problems
- dynamical systems
- partially observable environments
- hidden state
- markov decision problems
- action models
- reward function
- partially observable domains
- function approximation
- partial observations
- initially unknown
- infinite horizon
- random walk
- optimal policy
- fully observable
- learning algorithm
- transfer learning
- reinforcement learning algorithms
- belief state
- markov decision process
- dynamic environments
- machine learning
- multi agent
- optimal control
- policy iteration
- partially observable markov decision processes
- partially observable markov decision process
- decentralized control
- temporal difference
- model free