RESEARCH

R2D-RL: A RoboCup 2D Soccer Environment for Multi-Agent Reinforcement Learning

ArXiv cs.AI · Thu, 18 Jun 2026 04:00:00 GMT

arXiv:2606.18786v1 Announce Type: new Abstract: Robot soccer is a challenging testbed for multi-agent reinforcement learning because it combines partial observability, cooperative and adversarial interaction, sparse rewards, and long-horizon tactical behavior. RoboCup 2D Soccer S

Read original source Discuss with A.S.I.S