Meta-Reinforcement Learning Based Resource Allocation for Dynamic V2X Communications

This paper studies the allocation of shared resources between vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) links in vehicle-to-everything (V2X) communications. In existing algorithms, dynamic vehicular environments quantization continuous power become bottlenecks for providing an effective timely resource policy. this paper, we develop two algorithms to deal with these difficulties. First, propose a deep reinforcement learning (DRL)-based algorithm improve performance both V2I V2V links. Specifically, uses Q-network (DQN) solve sub-band assignment deterministic policy-gradient (DDPG) problem. Second, meta-based DRL enhance fast adaptability policy environment. Numerical results demonstrate that proposed DRL-based can significantly compared DQN-based quantizes power. addition, achieve required adaptation new environment limited experiences.