Indoor autonomous driving testbeds have emerged to complement expensive outdoor testbeds and virtual simulations, offering scalable and cost-effective solutions for research in navigation, traffic optimization, and swarm intelligence. However, they often lack the robust sensing and computing infrastructure for advanced research. Addressing these limitations, we introduce the Indoor Connected Autonomous Testbed (ICAT), a platform that not only tackles the unique challenges of indoor autonomous driving but also innovates vehicle computing and V2X communication. Moreover, ICAT leverages digital twins through CARLA and SUMO simulations, facilitating both centralized and decentralized autonomy deployments.

Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to divide and distribute the subtasks between the participating agents to carry out the main task. In contrast, we propose to learn a human constraints model that, in addition, considers the diverse behaviors of different human operators. We consider a type of collaboration in a shared-autonomy fashion, where both a human operator and an assistive robot act simultaneously in the same task space that affects each other's actions. The task of the assistive agent is to augment the skill of humans to perform a shared task by supporting humans as much as possible, both in terms of reducing the workload and minimizing the discomfort for the human operator. Therefore, we propose an augmentative assistant agent capable of learning and adapting to human physical constraints, aligning its actions with the ergonomic preferences and limitations of the human operator.

It is well-known in social choice that people may misreport their preferences to improve group decisions in their favor. Consider, for example, Alice, Bob, and Charlie deciding on which ice cream flavor to order for a party, and Charlie prefers strawberry to chocolate to vanilla. Given that Alice wants chocolate and Bob wants vanilla, Charlie would be better off voting for chocolate than truthfully (i.e., strawberry), by which vanilla may win as the tie-breaker. This form of strategic behavior is prolific in political science in narrowing the number of political parties (see e.g., Duvuger's law [Riker, 1982]). Still, it is unclear what effect strategic behavior has on the social welfare of chosen outcomes. Iterative voting (IV) is one model which naturally describes agents' strategic behavior - in misreporting their truthful preferences - over time. After agents reveal their preferences initially, they have the opportunity to repeatedly update their votes given information about other agents' votes, before the final decision is reached. Meir et al. [2010] first proposed iterative plurality voting and identified many sufficient conditions for IV to converge. This was followed up by a series of work examining various social choice rules, information and behavioral assumptions, and settings to determine when, to what outcomes, and how fast IV converges (see e.g.

With the development of deep learning, natural language processing technology has effectively improved the efficiency of various aspects of the traditional judicial industry. However, most current efforts focus solely on individual judicial stage, overlooking cross-stage collaboration. As the autonomous agents powered by large language models are becoming increasingly smart and able to make complex decisions in real-world settings, offering new insights for judicial intelligence. In this paper, (1) we introduce SimuCourt, a judicial benchmark that encompasses 420 judgment documents from real-world, spanning the three most common types of judicial cases, and a novel task Judicial Decision-Making to evaluate the judicial analysis and decision-making power of agents. To support this task, we construct a large-scale judicial knowledge base, JudicialKB, with multiple legal knowledge. (2) we propose a novel multi-agent framework, AgentsCourt. Our framework follows the real-world classic court trial process, consisting of court debate simulation, legal information retrieval and judgement refinement to simulate the decision-making of judge. (3) we perform extensive experiments, the results demonstrate that, our framework outperforms the existing advanced methods in various aspects, especially in generating legal grounds, where our model achieves significant improvements of 8.6% and 9.1% F1 score in the first and second instance settings, respectively.

This paper proposes a scalable distributed policy gradient method and proves its convergence to near-optimal solution in multi-agent linear quadratic networked systems. The agents engage within a specified network under local communication constraints, implying that each agent can only exchange information with a limited number of neighboring agents. On the underlying graph of the network, each agent implements its control input depending on its nearby neighbors' states in the linear quadratic control setting. We show that it is possible to approximate the exact gradient only using local information. Compared with the centralized optimal controller, the performance gap decreases to zero exponentially as the communication and control ranges increase. We also demonstrate how increasing the communication range enhances system stability in the gradient descent process, thereby elucidating a critical trade-off. The simulation results verify our theoretical findings.

As intelligent agents transition from controlled to uncontrolled environments, they face challenges that sometimes exceed their operational capabilities. In many scenarios, they rely on assistance from bystanders to overcome those challenges. Using robots that get stuck in urban settings as an example, we investigate how agents can prompt bystanders into providing assistance. We conducted four focus group sessions with 17 participants that involved bodystorming, where participants assumed the role of robots and bystander pedestrians in role-playing activities. Generating insights from both assumed robot and bystander perspectives, we were able to identify potential non-verbal help-seeking strategies (i.e., addressing bystanders, cueing intentions, and displaying emotions) and factors shaping the assistive behaviours of bystanders. Drawing on these findings, we offer design considerations for help-seeking urban robots and other agents operating in uncontrolled environments to foster casual collaboration, encompass expressiveness, align with agent social categories, and curate appropriate incentives.

We study data corruption robustness in offline two-player zero-sum Markov games. Given a dataset of realized trajectories of two players, an adversary is allowed to modify an $\epsilon$-fraction of it. The learner's goal is to identify an approximate Nash Equilibrium policy pair from the corrupted data. We consider this problem in linear Markov games under different degrees of data coverage and corruption. We start by providing an information-theoretic lower bound on the suboptimality gap of any learner. Next, we propose robust versions of the Pessimistic Minimax Value Iteration algorithm, both under coverage on the corrupted data and under coverage only on the clean data, and show that they achieve (near)-optimal suboptimality gap bounds with respect to $\epsilon$. We note that we are the first to provide such a characterization of the problem of learning approximate Nash Equilibrium policies in offline two-player zero-sum Markov games under data corruption.

Training for multi-agent reinforcement learning(MARL) is a time-consuming process caused by distribution shift of each agent. One drawback is that strategy of each agent in MARL is independent but actually in cooperation. Thus, a vertical issue in multi-agent reinforcement learning is how to efficiently accelerate training process. To address this problem, current research has leveraged a centralized function(CF) across multiple agents to learn contribution of the team reward for each agent. However, CF based methods introduce joint error from other agents in estimation of value network. In so doing, inspired by federated learning, we propose three simple novel approaches called Average Periodically Parameter Sharing(A-PPS), Reward-Scalability Periodically Parameter Sharing(RS-PPS) and Partial Personalized Periodically Parameter Sharing(PP-PPS) mechanism to accelerate training of MARL. Agents share Q-value network periodically during the training process. Agents which has same identity adapt collected reward as scalability and update partial neural network during period to share different parameters. We apply our approaches in classical MARL method QMIX and evaluate our approaches on various tasks in StarCraft Multi-Agent Challenge(SMAC) environment. Performance of numerical experiments yield enormous enhancement, with an average improvement of 10\%-30\%, and enable to win tasks that QMIX cannot. Our code can be downloaded from https://github.com/ColaZhang22/PPS-QMIX

Laboratory experiments have shown that communication plays an important role in solving social dilemmas. Here, by extending the AI-Economist, a mixed motive multi-agent reinforcement learning environment, I intend to find an answer to the following descriptive question: which governing system does facilitate the emergence and evolution of communication and teaching among agents? To answer this question, the AI-Economist is extended by a voting mechanism to simulate three different governing systems across individualistic-collectivistic axis, from full-libertarian to Full-Utilitarian governing systems. Moreover, the AI-Economist is further extended to include communication with possible misalignment, a variant of signalling game, by letting agents to build houses together if they are able to name mutually complement material resources by the same letter. Moreover, another extension is made to the AI-Economist to include teaching with possible misalignment, again a variant of signalling game, by letting half the agents as teachers who know how to use mutually complement material resources to build houses but are not capable of building actual houses, and the other half as students who do not have this information but are able to actually build those houses if teachers teach them. I found a strong evidence that collectivistic environment such as Full-Utilitarian system is more favourable for the emergence of communication and teaching, or more precisely, evolution of language alignment. Moreover, I found some evidence that evolution of language alignment through communication and teaching under collectivistic governing systems makes individuals more advantageously inequity averse. As a result, there is a positive correlation between evolution of language alignment and equality in the society.

Gradient-type distributed optimization methods have blossomed into one of the most important tools for solving a minimization learning task over a networked agent system. However, only one gradient update per iteration is difficult to achieve a substantive acceleration of convergence. In this paper, we propose an accelerated framework named as MUSIC allowing each agent to perform multiple local updates and a single combination in each iteration. More importantly, we equip inexact and exact distributed optimization methods into this framework, thereby developing two new algorithms that exhibit accelerated linear convergence and high communication efficiency. Our rigorous convergence analysis reveals the sources of steady-state errors arising from inexact policies and offers effective solutions. Numerical results based on synthetic and real datasets demonstrate both our theoretical motivations and analysis, as well as performance advantages.