Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information.
Eike-Manuel BansbachVictor EliachevitchLaurent SchmalenPublished in: GLOBECOM (2021)
Keyphrases
- resource allocation
- state information
- reinforcement learning
- state space
- action space
- resource management
- wireless networks
- resource allocation problems
- markov decision processes
- wireless communication
- optimal resource allocation
- real valued
- heuristic search
- reinforcement learning algorithms
- action models
- optimal policy
- allocation strategies
- markov decision process
- transfer learning
- partially observable
- optimal control
- allocation problems
- multi agent
- learning algorithm
- scarce resources
- distributed resource allocation
- learning process
- machine learning
- action selection
- orders of magnitude
- power allocation
- resource allocation and scheduling
- combinatorial auctions
- dynamic programming
- cooperative
- packet scheduling