The Sharing of Similar Knowledge on Monte Carlo Algorithm applies to Cryptocurrency Trading Problem

Abstract

Monte Carlo Algorithm is one of the various algorithms of Reinforcement Learning. It is used with problems that have finite states because of the memory problem. It must remember all the experiences to learn and make a decision. If the agent faces an unseen state, The Agent cannot use the experience for the decision to take the action. With these problems, we proposed the algorithm named The Sharing of Similar Knowledge on Monte Carlo Algorithm (SSKMC) to help Monte Carlo conducted with infinite states and leverage the old experience to decide the action when the agent faces a new experience (unseen state). In this paper, we tested the proposed algorithm with the Cryptocurrency Trading problem (Bitcoin) and compared the testing result of the proposed algorithm to Deep Reinforcement Learning (DRL). By the testing result of The Proposed algorithm makes net worth growth more than the DRL method by 1.55%.