RL-MADP: Reinforcement Learning-based Misdirection Attack Prevention Technique for WSN.
Iqra MustafaSheraz AslamMuhammad Bilal QureshiNouman AshrafShahzad AslamSyed Muhammad MohsinHasnain MustafaPublished in: IWCMC (2020)
Keyphrases
- reinforcement learning
- wireless sensor networks
- function approximation
- reinforcement learning algorithms
- model free
- state space
- energy efficient
- rl algorithms
- control problems
- sensor nodes
- reinforcement learning methods
- energy consumption
- supervised learning
- denial of service
- markov decision processes
- action selection
- routing protocol
- data aggregation
- resource constrained
- sensor networks
- multi agent
- temporal difference
- resource limitations
- policy iteration
- optimal policy
- learning problems
- action space
- learning agents
- learning algorithm
- key management
- optimal control
- machine learning
- partially observable
- secret key
- learning classifier systems
- control policy
- learned knowledge
- countermeasures
- dynamic programming
- continuous state
- policy evaluation
- learning process
- partially observable domains