A Fundamental Discussion on Reward-Based Reinforcement Learning for Uplink Resource Allocation in NTN.
Frodouard MinaniMakoto KobayashiTakuya FujihashiMd Abdul AlimShunsuke SaruwatariMasahiro NishiTakashi WatanabePublished in: ICMU (2023)
Keyphrases
- resource allocation
- reinforcement learning
- resource management
- resource allocation problems
- state space
- function approximation
- optimal resource allocation
- reinforcement learning algorithms
- multi agent
- allocation strategies
- long term evolution
- optimal policy
- markov decision processes
- market equilibrium
- resource allocation decisions
- allocate resources
- machine learning
- learning algorithm
- reward function
- model free
- resource requirements
- power allocation
- packet scheduling
- resource allocation and scheduling
- resource availability
- resource usage
- learning agent
- temporal difference
- combinatorial auctions
- allocation problems
- dynamic resource allocation
- grid environment
- distributed resource allocation
- learning process
- cooperative