AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning

Hayeong Lee, JunHyeok Oh, Byung-Jun Lee

ICML 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping

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 centralized value learning (MAPPO) instead of independent learning (IPPO) in scenarios needing global information (clover, ribbon)MAPPO · TABX clover/ribbonvalue estimation errorImproved
use centralized critic instead of independent learning where local observations suffice (crossfire, vsrangers, ambush)MAPPO · TABX crossfire/vsrangers/ambushwin rateHurt
QMIX monotonic value decomposition vs IQLQMIX · TABX scenarioswin rateImproved
add RND intrinsic reward on global state to MAPPO (ablation)MAPPO · TABX pingpong and encirclementwin rateImproved
raise entropy coefficient to 0.01 in MAPPO (ablation)MAPPO · TABX encirclementwin rateImproved
replay-based UED (PLR, ACCEL, SFL) instead of domain randomization when varying unit specificationsMAPPO · TABX zero-shot unit specificationszero-shot win rateHurt
train with health variation only vs speed or attack damage variation only (ablation)UED baselines · TABX zero-shot generalizationzero-shot win rateHurt
UED methods on unit-specification generalizationUED baselines · TABX unseen unit specificationsaverage win rate: below 50%No clear effect
recompilation-free reconfiguration in TABX vs SMAXTABX · 100 random scenario resetsenvironment steps per secondImproved
TABX vs SMAX in fixed configurationTABX · fixed configuration throughputenvironment steps per secondHurt

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