A Decentralized Communication Policy for Multi Agent Multi Armed Bandit Problems
This addresses efficient coordination in distributed learning systems for applications like sensor networks or robotics, though it is incremental as it builds on existing UCB and communication strategies.
The paper tackles the problem of multi-agent multi-armed bandit (MAB) by proposing a decentralized communication policy that combines UCB-based option selection with targeted communication to neighbors likely exploring, resulting in significant performance improvement over random communication policies and cost-effective scalability.
This paper proposes a novel policy for a group of agents to, individually as well as collectively, solve a multi armed bandit (MAB) problem. The policy relies solely on the information that an agent has obtained through sampling of the options on its own and through communication with neighbors. The option selection policy is based on an Upper Confidence Based (UCB) strategy while the communication strategy that is proposed forces agents to communicate with other agents who they believe are most likely to be exploring than exploiting. The overall strategy is shown to significantly outperform an independent Erdős-Rényi (ER) graph based random communication policy. The policy is shown to be cost effective in terms of communication and thus to be easily scalable to a large network of agents.