Overview: This project focuses on utilizing Reinforcement Learning (RL) techniques, specifically Deep Q-Network (DQN), for algorithmic trading. The algorithm learns to make trading decisions based on historical Bitcoin data, aiming to maximize profit by autonomously deciding whether to buy, sell, or hold stocks.
Reinforcement Learning (RL): Reinforcement Learning is a type of machine learning where an agent learns to make decisions by interacting with an environment. It learns through trial and error, receiving feedback in the form of rewards or penalties for its actions. RL aims to find an optimal policy that maximizes cumulative rewards over time.
Deep Q-Network (DQN): Deep Q-Network is a deep learning model used in RL, particularly in discrete action spaces. It combines Q-learning, a popular RL algorithm, with deep neural networks to approximate the Q-function, which represents the expected cumulative reward for taking a particular action in a given state.