In this paper, we propose a novel model-based multi-agent reinforcement learning approach named Value Decomposition Framework with Disentangled World Model to address the challenge of achieving a common goal of multiple agents interacting in the same environment with reduced sample complexity. Due to scalability and non-stationarity problems posed by multi-agent systems, model-free methods rely on a considerable number of samples for training. In contrast, we use a modularized world model, composed of action-conditioned, action-free, and static branches, to unravel the environment dynamics and produce imagined outcomes based on past experience, without sampling directly from the real environment. We employ variational auto-encoders and variational graph auto-encoders to learn the latent representations for the world model, which is merged with a value-based framework to predict the joint action-value function and optimize the overall training objective. We present experimental results in Easy, Hard, and Super-Hard StarCraft II micro-management challenges to demonstrate that our method achieves high sample efficiency and exhibits superior performance in defeating the enemy armies compared to other baselines.

Graph structured data are widely existed and applied in the real-world applications, while it is a challenge to handling these diverse data and learning tasks on graph in an efficient manner. When facing the complicated graph learning tasks, experts have designed diverse Graph Neural Networks (GNNs) in recent years. They have also implemented AutoML in Graph, also known as AutoGraph, to automatically generate data-specific solutions. Despite their success, they encounter limitations in (1) managing diverse learning tasks at various levels, (2) dealing with different procedures in graph learning beyond architecture design, and (3) the huge requirements on the prior knowledge when using AutoGraph. In this paper, we propose to use Large Language Models (LLMs) as autonomous agents to simplify the learning process on diverse real-world graphs. Specifically, in response to a user request which may contain varying data and learning targets at the node, edge, or graph levels, the complex graph learning task is decomposed into three components following the agent planning, namely, detecting the learning intent, configuring solutions based on AutoGraph, and generating a response. The AutoGraph agents manage crucial procedures in automated graph learning, including data-processing, AutoML configuration, searching architectures, and hyper-parameter fine-tuning. With these agents, those components are processed by decomposing and completing step by step, thereby generating a solution for the given data automatically, regardless of the learning task on node or graph. The proposed method is dubbed Auto$^2$Graph, and the comparable performance on different datasets and learning tasks. Its effectiveness is demonstrated by its comparable performance on different datasets and learning tasks, as well as the human-like decisions made by the agents.

Several interesting problems in multi-robot systems can be cast in the framework of distributed optimization. Examples include multi-robot task allocation, vehicle routing, target protection and surveillance. While the theoretical analysis of distributed optimization algorithms has received significant attention, its application to cooperative robotics has not been investigated in detail. In this paper, we show how notable scenarios in cooperative robotics can be addressed by suitable distributed optimization setups. Specifically, after a brief introduction on the widely investigated consensus optimization (most suited for data analytics) and on the partition-based setup (matching the graph structure in the optimization), we focus on two distributed settings modeling several scenarios in cooperative robotics, i.e., the so-called constraint-coupled and aggregative optimization frameworks. For each one, we consider use-case applications, and we discuss tailored distributed algorithms with their convergence properties. Then, we revise state-of-the-art toolboxes allowing for the implementation of distributed schemes on real networks of robots without central coordinators. For each use case, we discuss their implementation in these toolboxes and provide simulations and real experiments on networks of heterogeneous robots.

Control barrier functions (CBFs) enable guaranteed safe multi-agent navigation in the continuous domain. The resulting navigation performance, however, is highly sensitive to the underlying hyperparameters. Traditional approaches consider fixed CBFs (where parameters are tuned apriori), and hence, typically do not perform well in cluttered and highly dynamic environments: conservative parameter values can lead to inefficient agent trajectories, or even failure to reach goal positions, whereas aggressive parameter values can lead to infeasible controls. To overcome these issues, in this paper, we propose online CBFs, whereby hyperparameters are tuned in real-time, as a function of what agents perceive in their immediate neighborhood. Since the explicit relationship between CBFs and navigation performance is hard to model, we leverage reinforcement learning to learn CBF-tuning policies in a model-free manner. Because we parameterize the policies with graph neural networks (GNNs), we are able to synthesize decentralized agent controllers that adjust parameter values locally, varying the degree of conservative and aggressive behaviors across agents. Simulations as well as real-world experiments show that (i) online CBFs are capable of solving navigation scenarios that are infeasible for fixed CBFs, and (ii), that they improve navigation performance by adapting to other agents and changes in the environment.

Social insects such as ants communicate via pheromones which allows them to coordinate their activity and solve complex tasks as a swarm, e.g. foraging for food. This behavior was shaped through evolutionary processes. In computational models, self-coordination in swarms has been implemented using probabilistic or simple action rules to shape the decision of each agent and the collective behavior. However, manual tuned decision rules may limit the behavior of the swarm. In this work we investigate the emergence of self-coordination and communication in evolved swarms without defining any explicit rule. We evolve a swarm of agents representing an ant colony. We use an evolutionary algorithm to optimize a spiking neural network (SNN) which serves as an artificial brain to control the behavior of each agent. The goal of the evolved colony is to find optimal ways to forage for food and return it to the nest in the shortest amount of time. In the evolutionary phase, the ants are able to learn to collaborate by depositing pheromone near food piles and near the nest to guide other ants. The pheromone usage is not manually encoded into the network; instead, this behavior is established through the optimization procedure. We observe that pheromone-based communication enables the ants to perform better in comparison to colonies where communication via pheromone did not emerge. We assess the foraging performance by comparing the SNN based model to a rule based system. Our results show that the SNN based model can efficiently complete the foraging task in a short amount of time. Our approach illustrates self coordination via pheromone emerges as a result of the network optimization. This work serves as a proof of concept for the possibility of creating complex applications utilizing SNNs as underlying architectures for multi-agent interactions where communication and self-coordination is desired.

Autonomous agents have long been a prominent research focus in both academic and industry communities. Previous research in this field often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and thus makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of web knowledge, large language models (LLMs) have demonstrated remarkable potential in achieving human-level intelligence. This has sparked an upsurge in studies investigating LLM-based autonomous agents. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of LLM-based autonomous agents from a holistic perspective. More specifically, we first discuss the construction of LLM-based autonomous agents, for which we propose a unified framework that encompasses a majority of the previous work. Then, we present a comprehensive overview of the diverse applications of LLM-based autonomous agents in the fields of social science, natural science, and engineering. Finally, we delve into the evaluation strategies commonly used for LLM-based autonomous agents. Based on the previous studies, we also present several challenges and future directions in this field.

Many large-scale distributed multi-agent systems exchange information over low-power communication networks. In particular, agents intermittently communicate state and control signals in robotic network applications, often with limited power over an unlicensed spectrum, prone to eavesdropping and denial-of-service attacks. In this paper, we argue that a widely popular low-power communication protocol known as LoRa is vulnerable to denial-of-service attacks by an unauthenticated attacker if it can successfully identify a target signal's bandwidth and spreading factor. Leveraging a structural pattern in the LoRa signal's instantaneous frequency representation, we relate the problem of jointly inferring the two unknown parameters to a classification problem, which can be efficiently implemented using neural networks.

Institute of Computer Science; University of T artu Abstract Over the past decades, cognitive neuroscientists and behavioral economists have recognized the value of describing the process of decision making in detail and modeling the emergence of decisions over time. For example, the time it takes to decide can reveal more about an agent's true hidden preferences than only the decision itself. Similarly, data that track the ongoing decision process such as eye movements or neural recordings contain critical information that can be exploited, even if no decision is made. Here, we argue that artificial intelligence (AI) research would benefit from a stronger focus on insights about how decisions emerge over time and incorporate related process data to improve AI predictions in general and human-AI interactions in particular. First, we introduce a highly established computational framework that assumes decisions to emerge from the noisy accumulation of evidence, and we present related empirical work in psychology, neuroscience, and economics. Next, we discuss to what extent current approaches in multi-agent AI do or do not incorporate process data and models of decision making. Finally, we outline how a more principled inclusion of the evidence-accumulation framework into the training and use of AI can help to improve human-AI interactions in the future. A framework for modeling the emergence of individual and social decisions Predicting human decisions has been a key topic of interest in psychology for over a century. Prospect theory has proven successful in doing so for economic choices by incorporating elements of risk tendencies, loss aversion, and probability weighting (Kahneman & Tversky, 1979).

A novel and fully distributed optimization method is proposed for the distributed robust convex program (DRCP) over a time-varying unbalanced directed network without imposing any differentiability assumptions. Firstly, a tractable approximated DRCP (ADRCP) is introduced by discretizing the semi-infinite constraints into a finite number of inequality constraints and restricting the right-hand side of the constraints with a proper positive parameter, which will be iteratively solved by a random-fixed projection algorithm. Secondly, a cutting-surface consensus approach is proposed for locating an approximately optimal consensus solution of the DRCP with guaranteed feasibility. This approach is based on iteratively approximating the DRCP by successively reducing the restriction parameter of the right-hand constraints and populating the cutting-surfaces into the existing finite set of constraints. Thirdly, to ensure finite-time convergence of the distributed optimization, a distributed termination algorithm is developed based on uniformly local consensus and zeroth-order optimality under uniformly strongly connected graphs. Fourthly, it is proved that the cutting-surface consensus approach converges within a finite number of iterations. Finally, the effectiveness of the approach is illustrated through a numerical example.

I explore two questions in this thesis: how can computer science be used to fight human trafficking? And how can computer vision create a sense of touch? I use natural language processing (NLP) to monitor the United States illicit massage industry (IMI), a multi-billion dollar industry that offers not just therapeutic massages but also commercial sexual services. Employees of this industry are often immigrant women with few job opportunities, leaving them vulnerable to fraud, coercion, and other facets of human trafficking. Monitoring spatiotemporal trends helps prevent trafficking in the IMI. By creating datasets with three publicly-accessible websites: Google Places, Rubmaps, and AMPReviews, combined with NLP techniques such as bag-of-words and Word2Vec, I show how to derive insights into the labor pressures and language barriers that employees face, as well as the income, demographics, and societal pressures affecting sex buyers. I include a call-to-action to other researchers given these datasets. I also consider how to creating synthetic financial data, which can aid with counter-trafficking in the banking sector. I use an agent-based model to create both tabular and payee-recipient graph data. I then consider the role of computer vision in making tactile sensors. I report on a novel sensor, the Digger Finger, that adapts the Gelsight sensor to finding objects in granular media. Changes include using a wedge shape to facilitate digging, replacing the internal lighting LEDs with fluorescent paint, and adding a vibrator motor to counteract jamming. Finally, I also show how to use a webcam and a printed reference marker, or fiducial, to create a low-cost six-axis force-torque sensor. This sensor is up to a hundred times less expensive than commercial sensors, allowing for a wider range of applications. For this and earlier chapters I release design files and code as open source.