Intelligent manufacturing is a new model that uses advanced technologies such as the Internet of Things, big data, and artificial intelligence to improve the efficiency and quality of manufacturing production. As an important support to promote the transformation and upgrading of the manufacturing industry, cloud service optimization has received the attention of researchers. In recent years, remarkable research results have been achieved in this field. For the sustainability of intelligent manufacturing platforms, in this paper we summarize the process of cloud service optimization for intelligent manufacturing. Further, to address the problems of dispersed optimization indicators and nonuniform/unstandardized definitions in the existing research, 11 optimization indicators that take into account three-party participant subjects are defined from the urgent requirements of the sustainable development of intelligent manufacturing platforms. Next, service optimization algorithms are classified into two categories, heuristic and reinforcement learning. After comparing the two categories, the current key techniques of service optimization are targeted. Finally, research hotspots and future research trends of service optimization are summarized.

Social learning plays an important role in the development of human intelligence. As children, we imitate our parents' speech patterns until we are able to produce sounds; we learn from them praising us and scolding us; and as adults, we learn by working with others. In this work, we survey the degree to which this paradigm -- social learning -- has been mirrored in machine learning. In particular, since learning socially requires interacting with others, we are interested in how embodied agents can and have utilised these techniques. This is especially in light of the degree to which recent advances in natural language processing (NLP) enable us to perform new forms of social learning. We look at how behavioural cloning and next-token prediction mirror human imitation, how learning from human feedback mirrors human education, and how we can go further to enable fully communicative agents that learn from each other. We find that while individual social learning techniques have been used successfully, there has been little unifying work showing how to bring them together into socially embodied agents.

This paper introduces a new multidimensional extension of the Hegselmann-Krause (HK) opinion dynamics model, where opinion proximity is not determined by a norm or metric. Instead, each agent trusts opinions within the Minkowski sum $\xi+\mathcal{O}$, where $\xi$ is the agent's current opinion and $\mathcal{O}$ is the confidence set defining acceptable deviations. During each iteration, agents update their opinions by simultaneously averaging the trusted opinions. Unlike traditional HK systems, where $\mathcal{O}$ is a ball in some norm, our model allows the confidence set to be non-convex and even unbounded. We demonstrate that the new model, referred to as SCOD (Set-based Confidence Opinion Dynamics), can exhibit properties absent in the conventional HK model. Some solutions may converge to non-equilibrium points in the state space, while others oscillate periodically. These ``pathologies'' disappear if the set $\mathcal{O}$ is symmetric and contains zero in its interior: similar to the usual HK model, SCOD then converges in a finite number of iterations to one of the equilibrium points. The latter property is also preserved if one agent is "stubborn" and resists changing their opinion, yet still influences the others; however, two stubborn agents can lead to oscillations.

When engaging in conversations, dialogue agents in a virtual simulation environment may exhibit their own emotional states that are unrelated to the immediate conversational context, a phenomenon known as self-emotion. This study explores how such self-emotion affects the agents' behaviors in dialogue strategies and decision-making within a large language model (LLM)-driven simulation framework. In a dialogue strategy prediction experiment, we analyze the dialogue strategy choices employed by agents both with and without self-emotion, comparing them to those of humans. The results show that incorporating self-emotion helps agents exhibit more human-like dialogue strategies. In an independent experiment comparing the performance of models fine-tuned on GPT-4 generated dialogue datasets, we demonstrate that self-emotion can lead to better overall naturalness and humanness. Finally, in a virtual simulation environment where agents have discussions on multiple topics, we show that self-emotion of agents can significantly influence the decision-making process of the agents, leading to approximately a 50% change in decisions.

Self-play, characterized by agents' interactions with copies or past versions of itself, has recently gained prominence in reinforcement learning. This paper first clarifies the preliminaries of self-play, including the multi-agent reinforcement learning framework and basic game theory concepts. Then it provides a unified framework and classifies existing self-play algorithms within this framework. Moreover, the paper bridges the gap between the algorithms and their practical implications by illustrating the role of self-play in different scenarios. Finally, the survey highlights open challenges and future research directions in self-play. This paper is an essential guide map for understanding the multifaceted landscape of self-play in RL.

Quantum Reinforcement Learning (QRL) offers potential advantages over classical Reinforcement Learning, such as compact state space representation and faster convergence in certain scenarios. However, practical benefits require further validation. QRL faces challenges like flat solution landscapes, where traditional gradient-based methods are inefficient, necessitating the use of gradient-free algorithms. This work explores the integration of metaheuristic algorithms -- Particle Swarm Optimization, Ant Colony Optimization, Tabu Search, Genetic Algorithm, Simulated Annealing, and Harmony Search -- into QRL. These algorithms provide flexibility and efficiency in parameter optimization. Evaluations in $5\times5$ MiniGrid Reinforcement Learning environments show that, all algorithms yield near-optimal results, with Simulated Annealing and Particle Swarm Optimization performing best. In the Cart Pole environment, Simulated Annealing, Genetic Algorithms, and Particle Swarm Optimization achieve optimal results, while the others perform slightly better than random action selection. These findings demonstrate the potential of Particle Swarm Optimization and Simulated Annealing for efficient QRL learning, emphasizing the need for careful algorithm selection and adaptation.

This paper introduces a new LLM based agent framework for simulating electric vehicle (EV) charging behavior, integrating user preferences, psychological characteristics, and environmental factors to optimize the charging process. The framework comprises several modules, enabling sophisticated, adaptive simulations. Dynamic decision making is supported by continuous reflection and memory updates, ensuring alignment with user expectations and enhanced efficiency. The framework's ability to generate personalized user profiles and real-time decisions offers significant advancements for urban EV charging management. Future work could focus on incorporating more intricate scenarios and expanding data sources to enhance predictive accuracy and practical utility.

Multi-agent learning algorithms have been successful at generating superhuman planning in a wide variety of games but have had little impact on the design of deployed multi-agent planners. A key bottleneck in applying these techniques to multi-agent planning is that they require billions of steps of experience. To enable the study of multi-agent planning at this scale, we present GPUDrive, a GPU-accelerated, multi-agent simulator built on top of the Madrona Game Engine that can generate over a million steps of experience per second. Observation, reward, and dynamics functions are written directly in C++, allowing users to define complex, heterogeneous agent behaviors that are lowered to high-performance CUDA. We show that using GPUDrive we are able to effectively train reinforcement learning agents over many scenes in the Waymo Motion dataset, yielding highly effective goal-reaching agents in minutes for individual scenes and generally capable agents in a few hours.

Machine learning has witnessed remarkable breakthroughs in recent years. As machine learning permeates various aspects of daily life, individuals and organizations increasingly interact with these systems, exhibiting a wide range of social and adversarial behaviors. These behaviors may have a notable impact on the behavior and performance of machine learning systems. Specifically, during these interactions, data may be generated by strategic individuals, collected by self-interested data collectors, possibly poisoned by adversarial attackers, and used to create predictors, models, and policies satisfying multiple objectives. As a result, the machine learning systems' outputs might degrade, such as the susceptibility of deep neural networks to adversarial examples (Shafahi et al., 2018; Szegedy et al., 2013) and the diminished performance of classic algorithms in the presence of strategic individuals (Ahmadi et al., 2021). Addressing these challenges is imperative for the success of machine learning in societal settings.

The prediction of surrounding vehicle trajectories is crucial for collision-free path planning. In this study, we focus on a scenario where a connected and autonomous vehicle (CAV) serves as the central agent, utilizing both sensors and communication technologies to perceive its surrounding traffics consisting of autonomous vehicles (AVs), connected vehicles (CVs), and human-driven vehicles (HDVs). Our trajectory prediction task is aimed at all the detected surrounding vehicles. To effectively integrate the multi-source data from both sensor and communication technologies, we propose a deep learning framework called MSMA utilizing a cross-attention module for multi-source data fusion. Vector map data is utilized to provide contextual information. The trajectory dataset is collected in CARLA simulator with synthesized data errors introduced. Numerical experiments demonstrate that in a mixed traffic flow scenario, the integration of data from different sources enhances our understanding of the environment. This notably improves trajectory prediction accuracy, particularly in situations with a high CV market penetration rate. The code is available at: https://github.com/xichennn/MSMA.