2 papers
cs.RO2021
Hiding Leader's Identity in Leader-Follower Navigation through Multi-Agent Reinforcement Learning
Ankur Deka, Wenhao Luo, Huao Li +2
Leader-follower navigation is a popular class of multi-robot algorithms where a leader robot leads the follower robots in a team. The leader has specialized capabilities or mission…
cs.AI2020
Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams
Ankur Deka, Katia Sycara
Multi agent strategies in mixed cooperative-competitive environments can be hard to craft by hand because each agent needs to coordinate with its teammates while competing with its…