Zhixuan Liang

Zhixuan Liang, Jiannong Cao, Shan Jiang et al.

Many real-world applications can be formulated as multi-agent cooperation problems, such as network packet routing and coordination of autonomous vehicles. The emergence of deep reinforcement learning (DRL) provides a promising approach for multi-agent cooperation through the interaction of the agents and environments. However, traditional DRL solutions suffer from the high dimensions of multiple agents with continuous action space during policy search. Besides, the dynamicity of agents' policies makes the training non-stationary. To tackle the issues, we propose a hierarchical reinforcement learning approach with high-level decision-making and low-level individual control for efficient policy search. In particular, the cooperation of multiple agents can be learned in high-level discrete action space efficiently. At the same time, the low-level individual control can be reduced to single-agent reinforcement learning. In addition to hierarchical reinforcement learning, we propose an opponent modeling network to model other agents' policies during the learning process. In contrast to end-to-end DRL approaches, our approach reduces the learning complexity by decomposing the overall task into sub-tasks in a hierarchical way. To evaluate the efficiency of our approach, we conduct a real-world case study in the cooperative lane change scenario. Both simulation and real-world experiments show the superiority of our approach in the collision rate and convergence speed.

Haolong Yan, Yeqing Shen, Xin Huang et al.

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC software and mobile Apps, are often complex and proprietary, making it difficult to obtain the comprehensive environment information needed for agent training and evaluation. This limitation hinders systematic investigation and benchmarking of agent navigation capabilities. To address this limitation, we introduce GUI Exploration Lab, a simulation environment engine for GUI agent navigation research that enables flexible definition and composition of screens, icons, and navigation graphs, while providing full access to environment information for comprehensive agent training and evaluation. Through extensive experiments, we find that supervised fine-tuning enables effective memorization of fundamental knowledge, serving as a crucial foundation for subsequent training. Building on this, single-turn reinforcement learning further enhances generalization to unseen scenarios. Finally, multi-turn reinforcement learning encourages the development of exploration strategies through interactive trial and error, leading to further improvements in screen navigation performance. We validate our methods on both static and interactive benchmarks, demonstrating that our findings generalize effectively to real-world scenarios. These findings demonstrate the advantages of reinforcement learning approaches in GUI navigation and offer practical guidance for building more capable and generalizable GUI agents.

Zhixuan Liang, Xingyu Zeng, Rui Zhao et al.

Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches to evaluating data informativeness predominantly focus on the data's distribution or intrinsic information content and do not directly correlate with downstream task performance, such as mean average precision (mAP) in object detection. Thus, we propose Performance-guided (i.e. mAP-guided) Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model output changes as informativeness. To address the combinatorial explosion challenge of batch sample selection and the non-differentiable correlation between model performance and selected batches, MGRAL skillfully employs a reinforcement learning-based sampling agent that optimizes selection using policy gradient with mAP improvement as reward. Moreover, to reduce the computational overhead of mAP estimation with unlabeled samples, MGRAL utilizes an unsupervised way with fast look-up tables, ensuring feasible deployment. We evaluate MGRAL's active learning performance on detection tasks over PASCAL VOC and COCO benchmarks. Our approach demonstrates the highest AL curve with convincing visualizations, establishing a new paradigm in reinforcement learning-driven active object detection.

Xiangchun Chen, Jiannong Cao, Zhixuan Liang et al.

Collaborative edge computing (CEC) has emerged as a promising paradigm, enabling edge nodes to collaborate and execute microservices from end devices. Microservice offloading, a fundamentally important problem, decides when and where microservices are executed upon the arrival of services. However, the dynamic nature of the real-world CEC environment often leads to inefficient microservice offloading strategies, resulting in underutilized resources and network congestion. To address this challenge, we formulate an online joint microservice offloading and bandwidth allocation problem, JMOBA, to minimize the average completion time of services. In this paper, we introduce a novel microservice offloading algorithm, DTDRLMO, which leverages deep reinforcement learning (DRL) and digital twin technology. Specifically, we employ digital twin techniques to predict and adapt to changing edge node loads and network conditions of CEC in real-time. Furthermore, this approach enables the generation of an efficient offloading plan, selecting the most suitable edge node for each microservice. Simulation results on real-world and synthetic datasets demonstrate that DTDRLMO outperforms heuristic and learning-based methods in average service completion time.