The Centralized Training with Decentralized Execution (CTDE) paradigm is widely used in cooperative multi-agent reinforcement learning. However, due to the representational limitations of traditional monotonic value decomposition methods, algorithms can underestimate optimal actions, leading policies to suboptimal solutions. To address this challenge, we propose Optimistic $\epsilon$-Greedy Exploration, focusing on enhancing exploration to correct value estimations. The underestimation arises from insufficient sampling of optimal actions during exploration, as our analysis indicated. We introduce an optimistic updating network to identify optimal actions and sample actions from its distribution with a probability of $\epsilon$ during exploration, increasing the selection frequency of optimal actions. Experimental results in various environments reveal that the Optimistic $\epsilon$-Greedy Exploration effectively prevents the algorithm from suboptimal solutions and significantly improves its performance compared to other algorithms.

Artificially intelligent (AI) agents that are capable of autonomous learning and independent decision-making hold great promise for addressing complex challenges across domains like transportation, energy systems, and manufacturing. However, the surge in AI systems' design and deployment driven by various stakeholders with distinct and unaligned objectives introduces a crucial challenge: how can uncoordinated AI systems coexist and evolve harmoniously in shared environments without creating chaos? To address this, we advocate for a fundamental rethinking of existing multi-agent frameworks, such as multi-agent systems and game theory, which are largely limited to predefined rules and static objective structures. We posit that AI agents should be empowered to dynamically adjust their objectives, make compromises, form coalitions, and safely compete or cooperate through evolving relationships and social feedback. Through this paper, we call for a shift toward the emergent, self-organizing, and context-aware nature of these systems.

In Group Trip Planning (GTP) Query Problem, we are given a city road network where a number of Points of Interest (PoI) have been marked with their respective categories (e.g., Cafeteria, Park, Movie Theater, etc.). A group of agents want to visit one PoI from every category from their respective starting location and once finished, they want to reach their respective destinations. This problem asks which PoI from every category should be chosen so that the aggregated travel cost of the group is minimized. This problem has been studied extensively in the last decade, and several solution approaches have been proposed. However, to the best of our knowledge, none of the existing studies have considered the different modalities of the journey, which makes the problem more practical. To bridge this gap, we introduce and study the GTP Query Problem with Multimodal Journey in this paper. Along with the other inputs of the GTP Query Problem, we are also given the different modalities of the journey that are available and their respective cost. Now, the problem is not only to select the PoIs from respective categories but also to select the modality of the journey. For this problem, we have proposed an efficient solution approach, which has been analyzed to understand their time and space requirements. A large number of experiments have been conducted using real-life datasets and the results have been reported. From the results, we observe that the PoIs and modality of journey recommended by the proposed solution approach lead to much less time and cost than the baseline methods.

Predicting the future trajectories of surrounding traffic participants plays an essential role in automated driving. By anticipating future movements of nearby agents, such as vehicles and vulnerable road users, an automated vehicle (AV) can better plan maneuvers, reduce the risk of collisions, and ensure smoother interactions with other road users. Although existing approaches, e.g., [1-3], effectively predict the future movements of individual traffic participants, they limit an AV to a reactive planning strategy, assuming that the predictions of surrounding vehicles remain unaffected by the AV's planned actions. In highly interactive situations, this often leads to the freezing robot problem [4], where the AV, unable to engage in cooperative planning, simply stops to avoid potential collisions. For example, when it is unable to merge in dense traffic because the predictions of surrounding vehicles do not react to the AV's plan. One approach to resolving this is to condition the prediction on the AV's plan, often referred to as conditional inference [5].

Credit assignment, the process of attributing credit or blame to individual agents for their contributions to a team's success or failure, remains a fundamental challenge in multi-agent reinforcement learning (MARL), particularly in environments with sparse rewards. Commonly-used approaches such as value decomposition often lead to suboptimal policies in these settings, and designing dense reward functions that align with human intuition can be complex and labor-intensive. In this work, we propose a novel framework where a large language model (LLM) generates dense, agent-specific rewards based on a natural language description of the task and the overall team goal. By learning a potential-based reward function over multiple queries, our method reduces the impact of ranking errors while allowing the LLM to evaluate each agent's contribution to the overall task. Through extensive experiments, we demonstrate that our approach achieves faster convergence and higher policy returns compared to state-of-the-art MARL baselines.

Having the ability to infer characteristics of autonomous agents would profoundly revolutionize defense, security, and civil applications. Our previous work was the first to demonstrate that supervised neural network time series classification (NN TSC) could rapidly predict the tactics of swarming autonomous agents in military contexts, providing intelligence to inform counter-maneuvers. However, most autonomous interactions, especially military engagements, are fraught with uncertainty, raising questions about the practicality of using a pretrained classifier. This article addresses that challenge by leveraging expected operational variations to construct a richer dataset, resulting in a more robust NN with improved inference performance in scenarios characterized by significant uncertainties. Specifically, diverse datasets are created by simulating variations in defender numbers, defender motions, and measurement noise levels. Key findings indicate that robust NNs trained on an enriched dataset exhibit enhanced classification accuracy and offer operational flexibility, such as reducing resources required and offering adherence to trajectory constraints. Furthermore, we present a new framework for optimally deploying a trained NN by the defenders. The framework involves optimizing defender trajectories that elicit adversary responses that maximize the probability of correct NN tactic classification while also satisfying operational constraints imposed on the defenders.

The paper studies the problem of steering multi-dimensional opinion in a social network. Assuming the society of desire consists of stubborn and regular agents, stubborn agents are considered as leaders who specify the desired opinion distribution as a distributed reward or utility function. In this context, each regular agent is seen as a follower, updating its bias on the initial opinion and influence weights by averaging their observations of the rewards their influencers have received. Assuming random graphs with reducible and irreducible topology specify the influences on regular agents, opinion evolution is represented as a containment control problem in which stability and convergence to the final opinion are proven.

Noncooperative multi-agent systems often face coordination challenges due to conflicting preferences among agents. In particular, agents acting in their own self-interest can settle on different equilibria, leading to suboptimal outcomes or even safety concerns. We propose an algorithm named trading auction for consensus (TACo), a decentralized approach that enables noncooperative agents to reach consensus without communicating directly or disclosing private valuations. TACo facilitates coordination through a structured trading-based auction, where agents iteratively select choices of interest and provably reach an agreement within an a priori bounded number of steps. A series of numerical experiments validate that the termination guarantees of TACo hold in practice, and show that TACo achieves a median performance that minimizes the total cost across all agents, while allocating resources significantly more fairly than baseline approaches.

The advancement of mobile agents has opened new opportunities for automating tasks on mobile devices. Training these agents requires large-scale high-quality data, which is costly using human labor. Given the vast number of mobile phone users worldwide, if automated data collection from them is feasible, the resulting data volume and the subsequently trained mobile agents could reach unprecedented levels. Nevertheless, two major challenges arise: (1) extracting high-level and low-level user instructions without involving human and (2) utilizing distributed data from diverse users while preserving privacy. To tackle these challenges, we propose FedMobileAgent, a collaborative framework that trains mobile agents using self-sourced data from diverse users. Specifically, it includes two techniques. First, we propose Auto-Annotation, which enables the automatic collection of high-quality datasets during users' routine phone usage with minimal cost. Second, we introduce adapted aggregation to improve federated training of mobile agents on non-IID user data, by incorporating both episode- and step-level distributions. In distributed settings, FedMobileAgent achieves performance comparable to centralized human-annotated models at less than 0.02\% of the cost, highlighting its potential for real-world applications.

Sports analytics has become both more professional and sophisticated, driven by the growing availability of detailed performance data. This progress enables applications such as match outcome prediction, player scouting, and tactical analysis. In soccer, the effective utilization of event and tracking data is fundamental for capturing and analyzing the dynamics of the game. However, there are two primary challenges: the limited availability of event data, primarily restricted to top-tier teams and leagues, and the scarcity and high cost of tracking data, which complicates its integration with event data for comprehensive analysis. Here we propose OpenSTARLab, an open-source framework designed to democratize spatio-temporal agent data analysis in sports by addressing these key challenges. OpenSTARLab includes the Pre-processing Package that standardizes event and tracking data through Unified and Integrated Event Data and State-Action-Reward formats, the Event Modeling Package that implements deep learning-based event prediction, alongside the RLearn Package for reinforcement learning tasks. These technical components facilitate the handling of diverse data sources and support advanced analytical tasks, thereby enhancing the overall functionality and usability of the framework. To assess OpenSTARLab's effectiveness, we conducted several experimental evaluations. These demonstrate the superior performance of the specific event prediction model in terms of action and time prediction accuracies and maintained its robust event simulation performance. Furthermore, reinforcement learning experiments reveal a trade-off between action accuracy and temporal difference loss and show comprehensive visualization. Overall, OpenSTARLab serves as a robust platform for researchers and practitioners, enhancing innovation and collaboration in the field of soccer data analytics.