🚀 Exciting news from our team!
Our paper “ReCoDe: Reinforcement Learning-based Dynamic Constraint Design for Multi-Agent Coordination” has been accepted for presentation at CoRL 2025 this September 🎉
🤝 Multi-agent coordination is a cornerstone of robotics and autonomous systems, but designing constraints that balance cooperation and efficiency remains a challenge. ReCoDe introduces a reinforcement learning framework that dynamically adapts constraints, enabling agents to coordinate more effectively in challenging environments. We’re looking forward to sharing this work with the community at CoRL and discussing how dynamic constraint design can open new directions for safe and reliable real-world multi-agent systems.
📍 If you’re attending CoRL this year, come see our presentation—we’d love to connect!
#CoRL2025 #MultiAgentSystems #ReinforcementLearning #Robotics #AIResearch