Recent years have witnessed a plethora of learning-based solutions for congestion control (CC) that demonstrate better performance over traditional TCP schemes. However, they fail to provide consistently good convergence properties, including {\em fairness}, {\em fast convergence} and {\em stability}, due to the mismatch between their objective functions and these properties. Despite being intuitive, integrating these properties into existing learning-based CC is challenging, because: 1) their training environments are designed for the performance optimization of single flow but incapable of cooperative multi-flow optimization, and 2) there is no directly measurable metric to represent these properties into the training objective function. We present Astraea, a new learning-based congestion control that ensures fast convergence to fairness with stability. At the heart of Astraea is a multi-agent deep reinforcement learning framework that explicitly optimizes these convergence properties during the training process by enabling the learning of interactive policy between multiple competing flows, while maintaining high performance. We further build a faithful multi-flow environment that emulates the competing behaviors of concurrent flows, explicitly expressing convergence properties to enable their optimization during training. We have fully implemented Astraea and our comprehensive experiments show that Astraea can quickly converge to fairness point and exhibit better stability than its counterparts. For example, \sys achieves near-optimal bandwidth sharing (i.e., fairness) when multiple flows compete for the same bottleneck, delivers up to 8.4$\times$ faster convergence speed and 2.8$\times$ smaller throughput deviation, while achieving comparable or even better performance over prior solutions.

Instead of making behavioral decisions directly from the exponentially expanding joint observational-action space, subtask-based multi-agent reinforcement learning (MARL) methods enable agents to learn how to tackle different subtasks. Most existing subtask-based MARL methods are based on hierarchical reinforcement learning (HRL). However, these approaches often limit the number of subtasks, perform subtask recognition periodically, and can only identify and execute a specific subtask within the predefined fixed time period, which makes them inflexible and not suitable for diverse and dynamic scenarios with constantly changing subtasks. To break through above restrictions, a \textbf{S}liding \textbf{M}ultidimensional t\textbf{A}sk window based m\textbf{U}ti-agent reinforcement learnin\textbf{G} framework (SMAUG) is proposed for adaptive real-time subtask recognition. It leverages a sliding multidimensional task window to extract essential information of subtasks from trajectory segments concatenated based on observed and predicted trajectories in varying lengths. An inference network is designed to iteratively predict future trajectories with the subtask-oriented policy network. Furthermore, intrinsic motivation rewards are defined to promote subtask exploration and behavior diversity. SMAUG can be integrated with any Q-learning-based approach. Experiments on StarCraft II show that SMAUG not only demonstrates performance superiority in comparison with all baselines but also presents a more prominent and swift rise in rewards during the initial training stage.

This paper introduces the first formalization, implementation and quantitative evaluation of Feint in Multi-Player Games. Our work first formalizes Feint from the perspective of Multi-Player Games, in terms of the temporal, spatial, and their collective impacts. The formalization is built upon Non-transitive Active Markov Game Model, where Feint can have a considerable amount of impacts. Then, our work considers practical implementation details of Feint in Multi-Player Games, under the state-of-the-art progress of multi-agent modeling to date (namely Multi-Agent Reinforcement Learning). Finally, our work quantitatively examines the effectiveness of our design, and the results show that our design of Feint can (1) greatly improve the reward gains from the game; (2) significantly improve the diversity of Multi-Player Games; and (3) only incur negligible overheads in terms of time consumption. We conclude that our design of Feint is effective and practical, to make Multi-Player Games more interesting.

Foundation models (FMs), such as Large Language Models (LLMs), have revolutionized software development by enabling new use cases and business models. We refer to software built using FMs as FMware. The unique properties of FMware (e.g., prompts, agents, and the need for orchestration), coupled with the intrinsic limitations of FMs (e.g., hallucination) lead to a completely new set of software engineering challenges. Based on our industrial experience, we identified 10 key SE4FMware challenges that have caused enterprise FMware development to be unproductive, costly, and risky. In this paper, we discuss these challenges in detail and state the path for innovation that we envision. Next, we present FMArts, which is our long-term effort towards creating a cradle-to-grave platform for the engineering of trustworthy FMware. Finally, we (i) show how the unique properties of FMArts enabled us to design and develop a complex FMware for a large customer in a timely manner and (ii) discuss the lessons that we learned in doing so. We hope that the disclosure of the aforementioned challenges and our associated efforts to tackle them will not only raise awareness but also promote deeper and further discussions, knowledge sharing, and innovative solutions across the software engineering discipline.

Ergodic search enables optimal exploration of an information distribution while guaranteeing the asymptotic coverage of the search space. However, current methods typically have exponential computation complexity in the search space dimension and are restricted to Euclidean space. We introduce a computationally efficient ergodic search method. Our contributions are two-fold. First, we develop a kernel-based ergodic metric and generalize it from Euclidean space to Lie groups. We formally prove the proposed metric is consistent with the standard ergodic metric while guaranteeing linear complexity in the search space dimension. Secondly, we derive the first-order optimality condition of the kernel ergodic metric for nonlinear systems, which enables efficient trajectory optimization. Comprehensive numerical benchmarks show that the proposed method is at least two orders of magnitude faster than the state-of-the-art algorithm. Finally, we demonstrate the proposed algorithm with a peg-in-hole insertion task. We formulate the problem as a coverage task in the space of SE(3) and use a 30-second-long human demonstration as the prior distribution for ergodic coverage. Ergodicity guarantees the asymptotic solution of the peg-in-hole problem so long as the solution resides within the prior information distribution, which is seen in the 100\% success rate.

In the last decades, there has been a deceleration in the rates of According to the World Bank [43], over six hundred and fifty million poverty reduction, suggesting that traditional redistributive approaches people (10% of the global population) still live in extreme poverty to poverty mitigation could be losing effectiveness, and and COVID-19 has particularly affected the poorest: the number alternative insights to advance the number one UN Sustainable of people living in extreme poverty rose by 11 % in 2020 [45]. In Development Goal are required. The criminalization of poor people this context, urgent and innovative measures are required to work has been denounced by several NGOs, and an increasing number towards poverty eradication, the number one UN Sustainable Development of voices suggest that discrimination against the poor (a phenomenon Goal. Traditional policies based on the redistribution of known as aporophobia) could be an impediment to mitigating wealth could be losing effectiveness, since there has been a deceleration poverty. In this paper, we present the novel Aporophobia in the poverty reduction rates throughout the last decades Agent-Based Model (AABM) to provide evidence of the correlation [12]. Artificial Intelligence tools can provide alternative insights to between aporophobia and poverty computationally. We present this global challenge.

Individual differences in learning behavior within social groups, whether in humans, other animals, or among robots, can have significant effects on collective task performance. This is because it can affect individuals' response to the environment and their interactions with each other. In recent years there has been rising interest in the question of how individual differences, whether in learning or other traits, affect collective outcomes: studied, for example, in social insect foraging behavior. Multi-robot, 'swarm' systems have a heritage of bioinspiration from such examples, and here we consider whether heterogeneity in a learning behavior called latent inhibition (LI) may be useful for a team of patrolling robots tasked with environmental monitoring and anomaly detection. Individuals with high LI can be seen as better at learning to be inattentive to irrelevant or unrewarding stimuli, while low LI individuals might be seen as 'distractible' and yet, more positively, more exploratory. We introduce a simple model of the effects of LI as the probability of re-searching a location for a reward (anomalous reading) where it has previously been found to be unrewarding (irrelevant). In simulated patrols, we find that a negatively skewed distribution of mostly high LI robots, and just a single low LI robot, is collectively most effective at monitoring dynamic environments. These results are an example of 'functional heterogeneity' in 'swarm engineering' and could inform predictions for ecological distributions of learning traits within social groups.

This is a summary paper of a use case of a Robotdog dedicated to guide visually impaired people in complex environment like a smart intersection. In such scenarios, the Robotdog has to autonomously decide whether it is safe to cross the intersection or not in order to further guide the human. We leverage data sharing and collaboration between the Robotdog and other autonomous systems operating in the same environment. We propose a system architecture for autonomous systems through a separation of a collaborative decision layer, to enable collective decision making processes, where data about the environment, relevant to the Robotdog decision, together with evidences for trustworthiness about other systems and the environment are shared.

Milind Tambe is the winner of the 2024 AAAI Award for Artificial Intelligence for the Benefit of Humanity. This award recognizes positive impacts of artificial intelligence to protect, enhance, and improve human life in meaningful ways. Milind gave an invited talk at the AAAI Conference on Artificial Intelligence, in which he spoke about some of the work that won him the award. For more than 15 years, Milind and his team have been focused on advancing AI and multi-agent systems for three purposes: public health, conservation, and public safety and security. The emphasis in all cases has been to optimise limited intervention resources.

Game-theoretic dynamics between AI agents could differ from traditional human-human interactions in various ways. One such difference is that it may be possible to accurately simulate an AI agent, for example because its source code is known. Our aim is to explore ways of leveraging this possibility to achieve more cooperative outcomes in strategic settings. In this paper, we study an interaction between AI agents where the agents run a recursive joint simulation. That is, the agents first jointly observe a simulation of the situation they face. This simulation in turn recursively includes additional simulations (with a small chance of failure, to avoid infinite recursion), and the results of all these nested simulations are observed before an action is chosen. We show that the resulting interaction is strategically equivalent to an infinitely repeated version of the original game, allowing a direct transfer of existing results such as the various folk theorems.