A reinforcement learning (RL)-based hybrid method for ground penetrating radar (GPR)-driven buried object detection.
Mahmut Nedim AlpdemirMehmet SezginPublished in: Neural Comput. Appl. (2024)
Keyphrases
- ground penetrating radar
- hybrid method
- reinforcement learning
- object detection
- function approximation
- state space
- hybrid algorithm
- learning algorithm
- markov decision processes
- reinforcement learning algorithms
- computer vision
- multi class
- rl algorithms
- model free
- multi agent
- support vector machine
- learning problems
- temporal difference
- optimal policy
- transfer learning
- machine learning
- optimal control
- state and action spaces
- direct policy search
- markov decision process
- policy search
- actor critic
- evolutionary methods
- temporal difference learning
- support vector
- exploration exploitation tradeoff
- autonomous learning
- learning agents
- function approximators
- action space
- learning agent
- action selection
- learning classifier systems
- dynamic programming
- object recognition