{"slug": "r2d-rl-a-robocup-2d-soccer-environment-for-multi-agent-reinforcement-learning", "title": "R2D-RL: A RoboCup 2D Soccer Environment for Multi-Agent Reinforcement Learning", "summary": "Researchers introduced R2D-RL, a reinforcement learning environment that bridges the RoboCup 2D Soccer Simulation platform with Python-based multi-agent reinforcement learning workflows. The environment supports full-field and scenario-based training with configurable opponents, discrete and hybrid action spaces, and reward shaping, providing a benchmark for multi-agent RL in robot soccer.", "body_md": "arXiv:2606.18786v1 Announce Type: new\nAbstract: 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 Simulation (RCSS2D) provides a mature robot-soccer platform, but its competition-oriented server-client architecture is difficult to use directly with modern Python-based MARL workflows. We introduce R2D-RL, a reinforcement learning environment that connects RCSS2D and HELIOS-based player clients to a Python MARL interface through shared-memory communication and cycle-level synchronization. R2D-RL supports full-field and scenario-based training with configurable opponents, Base discrete and Hybrid parameterized action spaces, action masks, expected possession value (EPV)-based reward shaping, and parallel execution. We provide front-goal scenarios and an 11-vs-11 full-field benchmark, together with baseline results.", "url": "https://wpnews.pro/news/r2d-rl-a-robocup-2d-soccer-environment-for-multi-agent-reinforcement-learning", "canonical_source": "https://arxiv.org/abs/2606.18786", "published_at": "2026-06-18 04:00:00+00:00", "updated_at": "2026-06-18 04:23:13.731075+00:00", "lang": "en", "topics": ["machine-learning", "robotics", "ai-research"], "entities": ["RoboCup", "R2D-RL", "RCSS2D", "HELIOS", "Python"], "alternates": {"html": "https://wpnews.pro/news/r2d-rl-a-robocup-2d-soccer-environment-for-multi-agent-reinforcement-learning", "markdown": "https://wpnews.pro/news/r2d-rl-a-robocup-2d-soccer-environment-for-multi-agent-reinforcement-learning.md", "text": "https://wpnews.pro/news/r2d-rl-a-robocup-2d-soccer-environment-for-multi-agent-reinforcement-learning.txt", "jsonld": "https://wpnews.pro/news/r2d-rl-a-robocup-2d-soccer-environment-for-multi-agent-reinforcement-learning.jsonld"}}