Research on dynamic pricing strategies for traditional apparel helps business managers better balance the dual objectives of profit maximization and cultural heritage preservation. This paper addresses the challenge of unknown demand distributions for traditional garments by employing deep reinforcement learning techniques. Specifically, it constructs a multi-objective dynamic pricing model for traditional apparel based on the Markov Decision Process (MDP). Furthermore, a multi-objective particle swarm algorithm, based on Deep Deterministic Policy Gradient (DDPG), is proposed to solve the dynamic pricing problem for traditional apparel. By comparing the Pareto optimal solutions obtained iteratively through the multi-objective particle swarm algorithm (MOPSO), the multi-objective hybrid particle swarm algorithm, and the multi-objective particle swarm algorithm based on DDPG, the algorithm based on DDPG demonstrates superior generality and convergence performance.