Automated Cryptocurrency Trading Bot Implementing DRL

A year ago, one thousand USD invested in Bitcoin (BTC) alone would have appreciated to three five hundred USD. Deep reinforcement learning (DRL) recent outstanding performance has opened up the possibilities predict price fluctuations changing markets and determine effective trading points, making a significant contribution finance sector. Several DRL methods been tested domain. However, this research proposes implementing proximal policy optimisation (PPO) algorithm, which not integrated into an automated system (ATS). Furthermore, behavioural biases human decision-making often cloud one’s judgement perform emotionally. ATS may alleviate these problems by identifying using best potential strategy for maximising profit over time. Motivated factors mentioned, aims develop stable, accurate, robust that implements deep neural network movements maximise investment returns performing optimal points. Experiments evaluations illustrated model outperformed baseline buy hold method exceeded models of other similar works.