The rapid growth of cryptocurrency markets and the increasing role of digital assets in the global financial system have created new challenges in the valuation and pricing of these assets. Unlike traditional financial assets, cryptocurrencies lack clearly defined cash flows and conventional valuation criteria, and their prices are influenced by various factors, including market conditions, investor behavior, trading volume, and information-related variables. Therefore, developing innovative and intelligent models for pricing digital assets has become an important research issue. This study aims to design a digital asset pricing model using deep reinforcement learning in cryptocurrency markets. The primary research question is whether deep reinforcement learning can provide an efficient and accurate framework for pricing digital assets. In addition, the study examines the following hypotheses: the application of deep reinforcement learning improves the accuracy of digital asset pricing, enhances the model’s adaptability to changing market conditions, and outperforms traditional asset pricing approaches.
From the perspective of purpose, this research is applied, while methodologically it is quantitative and model-based. Historical data related to cryptocurrency prices, trading volumes, and market indicators were collected and analyzed using deep reinforcement learning algorithms. The performance of the proposed model was evaluated through forecasting error metrics and efficiency assessment indicators. The findings indicate that the proposed model is capable of identifying complex and nonlinear patterns in cryptocurrency markets and, through continuous learning from the market environment, provides greater pricing accuracy than traditional methods. Furthermore, the results suggest that deep reinforcement learning can serve as an effective tool for financial decision-making and investment management in cryptocurrency markets. The study contributes to the growing literature on artificial intelligence in finance and provides a practical framework for improving digital asset valuation in highly dynamic financial environments.