Single-Agent Actor Critic for Decentralized Cooperative Driving

arXiv:2403.11914v1 Announce Type: new
Abstract: Active traffic management incorporating autonomous vehicles (AVs) promises a future with diminished congestion and enhanced traffic flow. However, developing algorithms for real-world application requires addressing the challenges posed by continuous traffic flow and partial observability. To bridge this gap and advance the field of active traffic management towards greater decentralization, we introduce a novel asymmetric actor-critic model aimed at learning decentralized cooperative driving policies for autonomous vehicles using single-agent reinforcement learning. Our approach employs attention …

abstract actor advance agent algorithms application arxiv autonomous autonomous vehicles avs bridge challenges congestion continuous cs.lg cs.ro decentralized driving flow future gap however management observability traffic traffic management type vehicles world