MLRS-RL: An Energy-Efficient Multilevel Routing Strategy Based on Reinforcement Learning in Multimodal UWSNs.
Zhao ZhaoChunfeng LiuXiaoyun GuangKeqiu LiPublished in: IEEE Internet Things J. (2023)
Keyphrases
- reinforcement learning
- exploration exploitation
- function approximation
- model free
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- multi agent
- exploration strategy
- optimal policy
- state space
- learning algorithm
- rl algorithms
- routing protocol
- routing algorithm
- multi modal
- reinforcement learning methods
- control policy
- energy efficient
- wireless sensor networks
- active learning
- control problems
- continuous state
- partially observable domains
- direct policy search
- temporal difference learning
- routing problem
- network topology
- learning problems
- function approximators
- partially observable markov decision processes
- policy gradient
- policy evaluation
- shortest path
- learning process
- machine learning