QMIND 2023 - A Reinforcement Learning Approach to Currency Arbitrage

This repo contains our implementation of the method proposed in the research paper "Solving NP-Hard Problems on Graphs With Extended AlphaGo Zero" by Kenshin Abe, Zijian Xu, Issei Sato, Masashi Sugiyama. We attempt to apply this method to the longest path problem, an NP-Hard graph problem not presented in the paper. We also include a live testing environment using the Kraken API and user interface for viewing this environment.