In multi-agent learning, agents must coordinate with each other in order to
succeed. For humans, this coordination is typically accomplished through the
use of language. In this work we perform a controlled study of human language
use in a competitive team-based game, and search for useful lessons for
structuring communication protocol between autonomous agents. We construct
Pow-Wow, a new dataset for studying situated goal-directed human communication.
Using the Pommerman game environment, we enlisted teams of humans to play
against teams of AI agents, recording their observations, actions, and
communications. We analyze the types of communications which result in
effective game strategies, annotate them accordingly, and present corpus-level
statistical analysis of how trends in communications affect game outcomes.
Based on this analysis, we design a communication policy for learning agents,
and show that agents which utilize communication achieve higher win-rates
against baseline systems than those which do not.

本研究通过设计 Pow-Wow 数据集，分析人类在团队竞技游戏中的语言使用，提炼有效的通信策略，并将其应用于多智能体学习中，结果表明使用通信的智能体胜率较不使用通信的基准系统高。

Pow-Wow：Pommerman 协作通信的数据集和研究

Pow-Wow: A Dataset and Study on Collaborative Communication in Pommerman

Over recent years, deep reinforcement learning has shown strong successes in
complex single-agent tasks, and more recently this approach has also been
applied to multi-agent domains. In this paper, we propose a novel approach,
called MAGnet, to multi-agent reinforcement learning (MARL) that utilizes a
relevance graph representation of the environment obtained by a self-attention
mechanism, and a message-generation technique inspired by the NerveNet
architecture. We applied our MAGnet approach to the Pommerman game and the
results show that it significantly outperforms state-of-the-art MARL solutions,
including DQN, MADDPG, and MCTS.

本文提出了一种新的多智能体强化学习方法 MAGnet，将深度强化学习、自我关注机制、神经网络结构等技术应用于 Pommerman 游戏，实验结果表明，MAGnet 在该游戏中显著优于现有的 MARL 解决方案，如 DQN，MADDPG 和 MCTS 等。