AI RESEARCH
Collaborating in Multi-Armed Bandits with Strategic Agents
arXiv CS.LG
•
ArXi:2605.13145v1 Announce Type: new We study collaborative learning in multi-agent Bayesian bandit problems, where strategic agents collectively solve the same bandit instance. While multiple agents can accelerate learning by sharing information, strategic agents might prefer to free-ride and avoid exploration. We consider a setting with persistent agents that participate in multiple time periods.