首页|Team-wise effective communication in multi-agent reinforcement learning
Team-wise effective communication in multi-agent reinforcement learning
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Springer Nature
Abstract Effective communication is crucial for the success of multi-agent systems, as it promotes collaboration for attaining joint objectives and enhances competitive efforts towards individual goals. In the context of multi-agent reinforcement learning, determining “whom”, “how” and “what” to communicate are crucial factors for developing effective policies. Therefore, we propose TeamComm, a novel framework for multi-agent communication reinforcement learning. First, it introduces a dynamic team reasoning policy, allowing agents to dynamically form teams and adapt their communication partners based on task requirements and environment states in cooperative or competitive scenarios. Second, TeamComm utilizes heterogeneous communication channels consisting of intra- and inter-team to achieve diverse information flow. Lastly, TeamComm leverages the information bottleneck principle to optimize communication content, guiding agents to convey relevant and valuable information. Through experimental evaluations on three popular environments with seven different scenarios, we empirically demonstrate the superior performance of TeamComm compared to existing methods.
NETL
NSTL
Springer Nature
