Graph Neural Networks with Model-based Reinforcement Learning for Multi-agent Systems
This addresses multi-agent coordination problems in applications like autonomous driving, but appears incremental as it combines existing GNN and MBRL techniques.
The paper tackles multi-agent system tasks like billiard-avoidance and autonomous driving by proposing a GNN for MBRL model that predicts agent states and trajectories with GNNs and uses CEM-optimized MPC for planning, achieving successful task completion.
Multi-agent systems (MAS) constitute a significant role in exploring machine intelligence and advanced applications. In order to deeply investigate complicated interactions within MAS scenarios, we originally propose "GNN for MBRL" model, which utilizes a state-spaced Graph Neural Networks with Model-based Reinforcement Learning to address specific MAS missions (e.g., Billiard-Avoidance, Autonomous Driving Cars). In detail, we firstly used GNN model to predict future states and trajectories of multiple agents, then applied the Cross-Entropy Method (CEM) optimized Model Predictive Control to assist the ego-agent planning actions and successfully accomplish certain MAS tasks.