AI Paper Atlas

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

AAAI 2020 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 30 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use Arena rather than the compared platformsFixed sequence of 1000 actions repeated 1000 times · Platform stochasticity studyBranches: 431.2 -> 922.4Improved
Apply isolated rewards to all agentsCrossroads · Crossroads isolated-reward setupCoordination behaviorHurt
Apply a shared collaborative reward for all agentsCrossroads · Crossroads collaborative-reward setupCoordination behaviorImproved
Use collaboration within teams and competition between teamsCrossroads · Crossroads mixed team setupTeam strategyImproved
Evaluate training with ranking in the released base population instead of episode rewardFive implemented baselines · Crossroads and PushBoxTraining-curve clarityImproved
Use Arena rather than ALE for a game of similar complexity, with parallel PPOBoomer and MsPacman · Simulation speed comparisonSimulation speedNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy