In recent years, penetration testing (pen-testing) has emerged as a crucial process for evaluating the security level of network infrastructures by simulating real-world cyber-attacks. Automating pen-testing through reinforcement learning (RL) facilitates more frequent assessments, minimizes human effort, and enhances scalability. However, real-world pen-testing tasks often involve incomplete knowledge of the target network system. Effectively managing the intrinsic uncertainties via partially observable Markov decision processes (POMDPs) constitutes a persistent challenge within the realm of pen-testing. Furthermore, RL agents are compelled to formulate intricate strategies to contend with the challenges posed by partially observable environments, thereby engendering augmented computational and temporal expenditures. To address these issues, this study introduces EPPTA (Efficient POMDP-Driven Penetration Testing Agent), an agent built on an asynchronous RL framework, designed for conducting pen-testing tasks within partially observable environments. We incorporate an implicit belief module in EPPTA, grounded on the belief update formula of the traditional POMDP model, which represents the agent’s probabilistic estimation of the current environment state. Furthermore, by integrating the algorithm with the high-performance RL framework, Sample Factory, EPPTA significantly reduces convergence time compared to existing pen-testing methods, resulting in an approximately 20-fold acceleration. Empirical results across various pen-testing scenarios validate EPPTA’s superior task reward performance and enhanced scalability, providing substantial support for efficient and advanced evaluation of network infrastructure security.