Reinforcement learning applied to finance

Abstract

The purpose of this work is to create an agent that can trade efficiently in the stock market. There is an implementation,proximal policy optimization (PPO) to train the agent and OpenAIGym to simulate a finical Market environment. The biggest problem of the trading market is there is no specific trading strategies, more often investor focuses on the risk and thus it becomes more of gambling. The deep learning community find research on Financial market less interesting because of the difficulty and the expensive nature of financial market. Main goal is to introduce a trading model using Reinforcement learning and neural network. The model will create a better solution of the current anomaly. The process gives confidence that this model will help the investor to find a safe yet profitable strategy.