In the current research, we integrate distinct learning modalities—Curriculum Learning (CL) and Reinforcement Learning (RL)—in an attempt to develop and optimize Music Emotion Recognition (MER) in piano performance. Classical approaches have never been successful when applied in the field of determining the degree of emotion in the music of the piano, owing to the substantial complexity required. Addressing this particular issue is the primary motivation for the present endeavour. In an approach that’s comparable to how human beings acquire information, it trains the RL agent CL in phases; such an approach improves the student’s learning model in understanding the diverse emotions expressed by musical compositions. A higher rating of performance can be achieved after learning the model to recognize emotions more effectively and precisely. A set of piano melodies with emotional content notes has been included in the EMOPIA repository for use when conducting the process of evaluation. In order to benchmark the proposed approach with different models, parameters including R2, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) were deployed. Studies indicate that the recommended approach accurately recognizes the emotions expressed by piano-playing music. In challenging tasks like MER, the significance of implementing the CL paradigm with the RL has been emphasized using the outcomes mentioned earlier.