Deakin University
johnstone-towardsdesigninga-.pdf (1.55 MB)

Towards designing a generic and comprehensive deep reinforcement learning framework

Download (1.55 MB)
Version 2 2024-06-06, 10:14
Version 1 2022-05-30, 10:00
journal contribution
posted on 2024-06-06, 10:14 authored by ND Nguyen, TT Nguyen, NT Pham, H Nguyen, DT Nguyen, TD Nguyen, Chee Peng LimChee Peng Lim, Michael JohnstoneMichael Johnstone, Asim BhattiAsim Bhatti, Douglas CreightonDouglas Creighton, S Nahavandi
AbstractReinforcement learning (RL) has emerged as an effective approach for building an intelligent system, which involves multiple self-operated agents to collectively accomplish a designated task. More importantly, there has been a renewed focus on RL since the introduction of deep learning that essentially makes RL feasible to operate in high-dimensional environments. However, there are many diversified research directions in the current literature, such as multi-agent and multi-objective learning, and human-machine interactions. Therefore, in this paper, we propose a comprehensive software architecture that not only plays a vital role in designing a connect-the-dots deep RL architecture but also provides a guideline to develop a realistic RL application in a short time span. By inheriting the proposed architecture, software managers can foresee any challenges when designing a deep RL-based system. As a result, they can expedite the design process and actively control every stage of software development, which is especially critical in agile development environments. For this reason, we design a deep RL-based framework that strictly ensures flexibility, robustness, and scalability. To enforce generalization, the proposed architecture also does not depend on a specific RL algorithm, a network configuration, the number of agents, or the type of agents.



Applied Intelligence




Berlin, Germany

Open access

  • Yes







Publication classification

C1 Refereed article in a scholarly journal