5 papers
PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context Distillation
Ahmet Onur Akman, RafaÅ Kucharski
Cooperative multi-agent reinforcement learning often assumes a fixed execution team, yet many decentralized systems must operate with varying numbers of active agents during deploy…
URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles
Ahmet Onur Akman, Anastasia Psarou, MichaÅ Hoffmann +5
Connected Autonomous Vehicles (CAVs) promise to reduce congestion in future urban networks, potentially by optimizing their routing decisions. Unlike for human drivers, these decis…
Impact of Collective Behaviors of Autonomous Vehicles on Urban Traffic Dynamics: A Multi-Agent Reinforcement Learning Approach
Ahmet Onur Akman, Anastasia Psarou, Zoltán György Varga +2
This study examines the potential impact of reinforcement learning (RL)-enabled autonomous vehicles (AV) on urban traffic flow in a mixed traffic environment. We focus on a simplif…
Collaboration Between the City and Machine Learning Community is Crucial to Efficient Autonomous Vehicles Routing
Anastasia Psarou, Ahmet Onur Akman, Åukasz Gorczyca +3
Autonomous vehicles (AVs), possibly using Multi-Agent Reinforcement Learning (MARL) for simultaneous route optimization, may destabilize traffic networks, with human drivers potent…
RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles
Ahmet Onur Akman, Anastasia Psarou, Åukasz Gorczyca +3
RouteRL is a novel framework that integrates multi-agent reinforcement learning (MARL) with a microscopic traffic simulation, facilitating the testing and development of efficient…