Research map / Multi-agent systems and games / Cooperative multi-agent RL
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
Yuhang Song, Andrzej Wojcicki, Thomas Lukasiewicz, Jianyi Wang, Abi Aryan, Zhenghua Xu, Mai Xu, Zihan Ding, Lianlong Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Arena rather than the compared platforms | Fixed sequence of 1000 actions repeated 1000 times · Platform stochasticity study | Branches: 431.2 -> 922.4 | Improved |
| Apply isolated rewards to all agents | Crossroads · Crossroads isolated-reward setup | Coordination behavior | Hurt |
| Apply a shared collaborative reward for all agents | Crossroads · Crossroads collaborative-reward setup | Coordination behavior | Improved |
| Use collaboration within teams and competition between teams | Crossroads · Crossroads mixed team setup | Team strategy | Improved |
| Evaluate training with ranking in the released base population instead of episode reward | Five implemented baselines · Crossroads and PushBox | Training-curve clarity | Improved |
| Use Arena rather than ALE for a game of similar complexity, with parallel PPO | Boomer and MsPacman · Simulation speed comparison | Simulation speed | No clear effect |
Closest papers by meaning
- Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence (NeurIPS 2024 · similarity 0.88)
- FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.88)
- Agent-as-a-Judge: Evaluate Agents with Agents (ICML 2025 · similarity 0.88)
- Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation (ICLR 2026 · similarity 0.88)
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning (NeurIPS 2025 · similarity 0.87)
- Agentick: A Unified Benchmark for General Sequential Decision-Making Agents (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
