Deep Reinforcement Learning-Assisted Age-optimal Transmission Policy for HARQ-aided NOMA Networks.
Kunpeng LiuAimin LiShaohua WuPublished in: INFOCOM Workshops (2023)
Keyphrases
- reinforcement learning
- control policy
- optimal policy
- dynamic programming
- control policies
- optimal control
- asymptotically optimal
- social networks
- total reward
- optimal solution
- worst case
- policy search
- action selection
- reinforcement learning problems
- function approximation
- markov decision processes
- approximate dynamic programming
- function approximators
- data transmission
- infinite horizon
- state space
- reinforcement learning algorithms
- partially observable
- continuous state spaces
- finite horizon
- continuous state
- learning algorithm
- partially observable environments
- scheduling policies
- state dependent
- action space
- policy iteration
- average cost
- expected cost
- reward function
- network structure
- multi agent