Log In Sign Up

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

by   Takuma Yoneda, et al.

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.


page 1

page 3


Knowledge-Based Strategies for Multi-Agent Teams Playing Against Nature

We study teams of agents that play against Nature towards achieving a co...

Teaming up with information agents

Despite the intricacies involved in designing a computer as a teampartne...

Commander's Intent: A Dataset and Modeling Approach for Human-AI Task Specification in Strategic Play

Effective Human-AI teaming requires the ability to communicate the goals...

Learning multiagent coordination in the absence of communication channels

In this work, we develop a reinforcement learning protocol for a multiag...

Understanding communications in medical emergency situations

Good communication is essential within teams dealing with emergency situ...

Decentralization of Multiagent Policies by Learning What to Communicate

Effective communication is required for teams of robots to solve sophist...