Adaptive Q-Network: On-the-fly Target Selection for Deep Reinforcement Learning.
Théo VincentFabian WahrenJan PetersBoris BelousovCarlo D'EramoPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- network model
- wireless sensor networks
- machine learning
- function approximation
- communication networks
- computer networks
- learning algorithm
- network structure
- adaptive control
- learning capabilities
- network traffic
- multi agent
- genetic algorithm
- optimal control
- target object
- data sets
- network architecture
- network design
- function approximators