Rui Zhong

Rui Zhong, Enzhi Zhang, Masaharu Munetomo

In this paper, we propose a two-stage optimization strategy for solving the Large-scale Traveling Salesman Problems (LSTSPs) named CCPNRL-GA. First, we hypothesize that the participation of a well-performed individual as an elite can accelerate the convergence of optimization. Based on this hypothesis, in the first stage, we cluster the cities and decompose the LSTSPs into multiple subcomponents, and each subcomponent is optimized with a reusable Pointer Network (PtrNet). After subcomponents optimization, we combine all sub-tours to form a valid solution, this solution joins the second stage of optimization with GA. We validate the performance of our proposal on 10 LSTSPs and compare it with traditional EAs. Experimental results show that the participation of an elite individual can greatly accelerate the optimization of LSTSPs, and our proposal has broad prospects for dealing with LSTSPs.

Zijian Zhang, Shuchang Liu, Ziru Liu et al.

User simulators can rapidly generate a large volume of timely user behavior data, providing a testing platform for reinforcement learning-based recommender systems, thus accelerating their iteration and optimization. However, prevalent user simulators generally suffer from significant limitations, including the opacity of user preference modeling and the incapability of evaluating simulation accuracy. In this paper, we introduce an LLM-powered user simulator to simulate user engagement with items in an explicit manner, thereby enhancing the efficiency and effectiveness of reinforcement learning-based recommender systems training. Specifically, we identify the explicit logic of user preferences, leverage LLMs to analyze item characteristics and distill user sentiments, and design a logical model to imitate real human engagement. By integrating a statistical model, we further enhance the reliability of the simulation, proposing an ensemble model that synergizes logical and statistical insights for user interaction simulations. Capitalizing on the extensive knowledge and semantic generation capabilities of LLMs, our user simulator faithfully emulates user behaviors and preferences, yielding high-fidelity training data that enrich the training of recommendation algorithms. We establish quantifying and qualifying experiments on five datasets to validate the simulator's effectiveness and stability across various recommendation scenarios.