In their work FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource Allocation, accepted at IJCAI 2024, Tianfu Wang, Qilin Fan, Chao Wang, Long Yang, Leilei Ding, Nicholas Jing Yuan and Hui Xiong introduce a framework for addressing resource allocation problems. In this interview, Tianfu Wang tells us more about their framework, the implications of their research, and what they are planning next. Our paper focuses on addressing resource allocation problems using a reinforcement learning (RL) framework, specifically in the domain of network virtualization, known as virtual network embedding (VNE). VNE involves efficiently mapping virtual network requests onto physical infrastructure. However, existing RL-based VNE methods are limited by the unidirectional action design and one-size-fits-all training strategy, resulting in restricted searchability and generalizability.

Virtual network embedding (VNE) is an essential resource allocation task in network virtualization, aiming to map virtual network requests (VNRs) onto physical infrastructure. Reinforcement learning (RL) has recently emerged as a promising solution to this problem. However, existing RL-based VNE methods are limited by the unidirectional action design and one-size-fits-all training strategy, resulting in restricted searchability and generalizability. In this paper, we propose a FLexible And Generalizable RL framework for VNE, named FlagVNE. Specifically, we design a bidirectional action-based Markov decision process model that enables the joint selection of virtual and physical nodes, thus improving the exploration flexibility of solution space. To tackle the expansive and dynamic action space, we design a hierarchical decoder to generate adaptive action probability distributions and ensure high training efficiency. Furthermore, to overcome the generalization issue for varying VNR sizes, we propose a meta-RL-based training method with a curriculum scheduling strategy, facilitating specialized policy training for each VNR size. Finally, extensive experimental results show the effectiveness of FlagVNE across multiple key metrics. Our code is available at GitHub (https://github.com/GeminiLight/flag-vne).