|
Full title—Meta-Hierarchical Reinforcement Learning (MHRL)-based Dynamic Resource Allocation for Dynamic Vehicular Networks
In this paper, the authors propose a general framework that can enable fast-adaptive resource allocation for dynamic vehicular environments. They combine hierarchical reinforcement learning with meta learning, which makes our proposed framework quickly adapt to a new environment by only fine-tuning the top-level master network, and meanwhile the low-level sub-networks can make the right resource allocation policy.
Full Article: IEEE Transactions on Vehicular Technology, Early Access | 
