Double RISs assisted task offloading for NOMA-MEC with action-constrained deep reinforcement learning.
Junli FangBaoshan LuXuemin HongJianghong ShiPublished in: Knowl. Based Syst. (2024)
Keyphrases
- reinforcement learning
- action selection
- partially observable domains
- action space
- reward shaping
- state action
- state space
- model free
- function approximation
- agent learns
- reinforcement learning algorithms
- temporal difference
- learning algorithm
- human actions
- continuous state
- transition model
- robotic control
- control policy
- policy search
- optimal policy
- state and action spaces
- deep learning
- action descriptions
- optimal control
- continuous action
- agent receives
- fitted q iteration