Reinforcement Learning (RL) has become a popular learning framework to solve sequential decision making problems in unknown environments, and has achieved tremendous success in a wide array of domains such as playing the game of Go (Silver et al., 2016), robotic control (Kober et al., 2013), and autonomous driving (Kiran et al., 2022; Lin et al., 2023). A critical feature of most real-world systems is their uncertain nature, and consequently RL has emerged as a powerful tool for learning optimal policies for multi-agent systems to operate in unknown environments (Kim & Giannakis, 2017; Zhang et al., 2021; Lin et al., 2024; Anand & Qu, 2024). While the early literature on RL predominantly focused on the single-agent setting, multi-agent reinforcement learning (MARL) has also recently achieved impressive successes in a broad range of areas, such as coordination of robotic swarms (Preiss et al., 2017), self-driving vehicles (DeWeese & Qu, 2024), real-time bidding (Jin et al., 2018), ride-sharing (Li et al., 2019), and stochastic games (Jin et al., 2020). Despite growing interest in multi-agent RL (MARL), extending RL to multi-agent settings poses significant computational challenges due to the curse of dimensionality (Sayin et al., 2021). Even if the individual agents' state or action spaces are small, the global state space or action space can take values from a set with size that is exponentially large as a function of the number of agents.

Advancements in Large Language Models (LLMs) have opened transformative possibilities for human-robot interaction, especially in collaborative environments. However, Real-time human-AI collaboration requires agents to adapt to unseen human behaviors while maintaining effective communication dynamically. Existing benchmarks fall short in evaluating such adaptability for embodied agents, focusing mostly on the task performance of the agent itself. To address this gap, we propose a novel benchmark that assesses agents' reactive adaptability and instantaneous communication capabilities at every step. Based on this benchmark, we propose a Monitor-then-Adapt framework (MonTA), combining strong adaptability and communication with real-time execution. MonTA contains three key LLM modules, a lightweight \textit{Monitor} for monitoring the need for adaptation in high frequency, and two proficient \textit{Adapters} for subtask and path adaptation reasoning in low frequency. Our results demonstrate that MonTA outperforms other baseline agents on our proposed benchmark. Further user studies confirm the high reasonability adaptation plan and consistent language instruction provided by our framework.

This paper presents an efficient algorithm for finding the power-optimal currents of magnetorquer, a satellite attitude actuator in Earth orbit, for multi-agent formation and attitude control. Specifically, this study demonstrates that a set of power-optimal solutions can be derived through sequential convex programming and proposes a method to approximate these solutions using a deep neural network (DNN). The practicality of this DNN model is demonstrated through numerical simulations of formation and attitude control.

The driving interaction--a critical yet complex aspect of daily driving--lies at the core of autonomous driving research. However, real-world driving scenarios sparsely capture rich interaction events, limiting the availability of comprehensive trajectory datasets for this purpose. To address this challenge, we present InterHub, a dense interaction dataset derived by mining interaction events from extensive naturalistic driving records. We employ formal methods to describe and extract multi-agent interaction events, exposing the limitations of existing autonomous driving solutions. Additionally, we introduce a user-friendly toolkit enabling the expansion of InterHub with both public and private data.

Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space created by unexpected faults. Second, transitions recorded before and after faults in the replay buffer affect training unevenly, leading to a sample imbalance problem. To overcome these challenges, this paper enhances the fault tolerance of MARL by combining optimized model architecture with a tailored training data sampling strategy. Specifically, an attention mechanism is incorporated into the actor and critic networks to automatically detect faults and dynamically regulate the attention given to faulty agents. Additionally, a prioritization mechanism is introduced to selectively sample transitions critical to current training needs. To further support research in this area, we design and open-source a highly decoupled code platform for fault-tolerant MARL, aimed at improving the efficiency of studying related problems. Experimental results demonstrate the effectiveness of our method in handling various types of faults, faults occurring in any agent, and faults arising at random times.

Building operations consume approximately 40% of global energy, with Heating, Ventilation, and Air Conditioning (HVAC) systems responsible for up to 50% of this consumption. As HVAC energy demands are expected to rise, optimising system efficiency is crucial for reducing future energy use and mitigating climate change. Existing control strategies lack generalisation and require extensive training and data, limiting their rapid deployment across diverse buildings. This paper introduces HVAC-DPT, a Decision-Pretrained Transformer using in-context Reinforcement Learning (RL) for multi-zone HVAC control. HVAC-DPT frames HVAC control as a sequential prediction task, training a causal transformer on interaction histories generated by diverse RL agents. This approach enables HVAC-DPT to refine its policy in-context, without modifying network parameters, allowing for deployment across different buildings without the need for additional training or data collection. HVAC-DPT reduces energy consumption in unseen buildings by 45% compared to the baseline controller, offering a scalable and effective approach to mitigating the increasing environmental impact of HVAC systems.

Industrial networks are undergoing rapid transformation driven by the convergence of emerging technologies that are revolutionizing conventional workflows, enhancing operational efficiency, and fundamentally redefining the industrial landscape across diverse sectors. Amidst this revolution, Digital Twin (DT) emerges as a transformative innovation that seamlessly integrates real-world systems with their virtual counterparts, bridging the physical and digital realms. In this article, we present a comprehensive survey of the emerging DT-enabled services and applications across industries, beginning with an overview of DT fundamentals and its components to a discussion of key enabling technologies for DT. Different from literature works, we investigate and analyze the capabilities of DT across a wide range of industrial services, including data sharing, data offloading, integrated sensing and communication, content caching, resource allocation, wireless networking, and metaverse. In particular, we present an in-depth technical discussion of the roles of DT in industrial applications across various domains, including manufacturing, healthcare, transportation, energy, agriculture, space, oil and gas, as well as robotics. Throughout the technical analysis, we delve into real-time data communications between physical and virtual platforms to enable industrial DT networking. Subsequently, we extensively explore and analyze a wide range of major privacy and security issues in DT-based industry. Taxonomy tables and the key research findings from the survey are also given, emphasizing important insights into the significance of DT in industries. Finally, we point out future research directions to spur further research in this promising area.

In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between agents with different languages without additional retraining. Our algorithm is based on relative representations, a framework that enables different agents employing different neural network models to have unified representation. It proceeds by projecting the latent vectors of different models into a common space defined relative to a set of data samples called \textit{anchors}, whose number equals the dimension of the resulting space. A communication between different agents translates to a communication of semantic symbols sampled from this relative space. This approach, in addition to aligning the semantic representations of different agents, allows compressing the amount of information being exchanged, by appropriately selecting the number of anchors. Eventually, we introduce a novel anchor selection strategy, which advantageously determines prototypical anchors, capturing the most relevant information for the downstream task. Our numerical results show the effectiveness of the proposed approach allowing seamless communication between agents with radically different models, including differences in terms of neural network architecture and datasets used for initial training.

Despite recent advances in learning-based behavioral planning for autonomous systems, decision-making in multi-task missions remains a challenging problem. For instance, a mission might require a robot to explore an unknown environment, locate the goals, and navigate to them, even if there are obstacles along the way. Such problems are difficult to solve due to: a) sparse rewards, meaning a reward signal is available only once all the tasks in a mission have been satisfied, and b) the agent having to perform tasks at run-time that are not covered in the training data, e.g., demonstrations only from an environment where all doors were unlocked. Consequently, state-of-the-art decision-making methods in such settings are limited to missions where the required tasks are well-represented in the training demonstrations and can be solved within a short planning horizon. To overcome these limitations, we propose Adaptformer, a stochastic and adaptive planner that utilizes sequence models for sample-efficient exploration and exploitation. This framework relies on learning an energy-based heuristic, which needs to be minimized over a sequence of high-level decisions. To generate successful action sequences for long-horizon missions, Adaptformer aims to achieve shorter sub-goals, which are proposed through an intrinsic sub-goal curriculum. Through these two key components, Adaptformer allows for generalization to out-of-distribution tasks and environments, i.e., missions that were not a part of the training data. Empirical results in multiple simulation environments demonstrate the effectiveness of our method. Notably, Adaptformer not only outperforms the state-of-the-art method by up to 25% in multi-goal maze reachability tasks but also successfully adapts to multi-task missions that the state-of-the-art method could not complete, leveraging demonstrations from single-goal-reaching tasks.

A popular approach of automated mechanism design is to formulate a linear program (LP) whose solution gives a mechanism with desired properties. We analytically derive a class of optimal solutions for such an LP that gives mechanisms achieving standard properties of efficiency, incentive compatibility, strong budget balance (SBB), and individual rationality (IR), where SBB and IR are satisfied in expectation. Notably, our solutions are represented by an exponentially smaller number of essential variables than the original variables of LP. Our solutions, however, involve a term whose exact evaluation requires solving a certain optimization problem exponentially many times as the number of players, $N$, grows. We thus evaluate this term by modeling it as the problem of estimating the mean reward of the best arm in multi-armed bandit (MAB), propose a Probably and Approximately Correct estimator, and prove its asymptotic optimality by establishing a lower bound on its sample complexity. This MAB approach reduces the number of times the optimization problem is solved from exponential to $O(N\,\log N)$. Numerical experiments show that the proposed approach finds mechanisms that are guaranteed to achieve desired properties with high probability for environments with up to 128 players, which substantially improves upon the prior work.