Timezone: »

 
Emergent collective intelligence from massive-agent cooperation and competition
Hanmo Chen · Stone Tao · JIAXIN CHEN · Weihan Shen · Xihui Li · Chenghui Yu · Sikai Cheng · Xiaolong Zhu · Xiu Li

@
in Deep Reinforcement Learning Workshop »
Event URL: https://openreview.net/forum?id=KCWm-HV0PQT »

Inspired by organisms evolving through cooperation and competition between different populations on Earth, we study the emergence of artificial collective intelligence through massive-agent reinforcement learning. To this end, We propose a new massive-agent reinforcement learning environment, Lux, where dynamic and massive agents in two teams scramble for limited resources and fight off the darkness. In Lux, we build our agents through the standard reinforcement learning algorithm in curriculum learning phases and leverage centralized control via a pixel-to-pixel policy network. As agents co-evolve through self-play, we observe several stages of intelligence, from the acquisition of atomic skills to the development of group strategies. Since these learned group strategies arise from individual decisions without an explicit coordination mechanism, we claim that artificial collective intelligence emerges from massive-agent cooperation and competition. We further analyze the emergence of various learned strategies through metrics and ablation studies, aiming to provide insights for reinforcement learning implementations in massive-agent environments.

[ Poster]  [ OpenReview]  [ Topia] 

Author Information

Hanmo Chen
Stone Tao (University of California - San Diego)
JIAXIN CHEN (The Hong Kong Polytechnic University)
Weihan Shen (University of Florida)
Xihui Li (Tsinghua University, Tsinghua University)
Chenghui Yu
Sikai Cheng (Georgia Institute of Technology)
Xiaolong Zhu (University of Hong Kong)
Xiu Li

More from the Same Authors