Learning to generate Reliable Broadcast Algorithms

TL;DR

This paper introduces a reinforcement learning-based method to automatically generate correct and efficient fault-tolerant Reliable Broadcast algorithms, reducing manual effort and achieving competitive performance in a limited number of episodes.

Contribution

It presents an innovative approach using reinforcement learning to automate the development of fault-tolerant distributed algorithms, specifically Reliable Broadcast.

Findings

Successfully generated correct Reliable Broadcast algorithms

Achieved performance comparable to existing algorithms

Completed learning in approximately 12,000 episodes

Abstract

Modern distributed systems are supported by fault-tolerant algorithms, like Reliable Broadcast and Consensus, that assure the correct operation of the system even when some of the nodes of the system fail. However, the development of distributed algorithms is a manual and complex process, resulting in scientific papers that usually present a single algorithm or variations of existing ones. To automate the process of developing such algorithms, this work presents an intelligent agent that uses Reinforcement Learning to generate correct and efficient fault-tolerant distributed algorithms. We show that our approach is able to generate correct fault-tolerant Reliable Broadcast algorithms with the same performance of others available in the literature, in only 12,000 learning episodes.