Portfolio optimisation is a core challenge in finance. Traditional models like Mean-Variance Optimisation rely on assumptions that often break down in real markets. In contrast, Reinforcement Learning (RL) offers a flexible, adaptive approach to sequential decision-making under uncertainty, making it well-suited to dynamic financial environments. Recent advances in deep RL (e.g., DQN, PPO, SAC) offer new opportunities to build data-driven investment strategies. However, applying RL in finance still poses key challenges in risk control, stability, and real-world applicability