MAgent

The 'MAgent' dataset/benchmark is used to evaluate cooperative multi-agent reinforcement learning (MARL) algorithms in environments that involve multiple agents interacting and communicating to achieve common goals.

Papers using MAgent (2)

Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning2025NVIF: Neighboring Variational Information Flow for Large-Scale Cooperative Multi-Agent Scenarios2022 · 1 cites