Recent advancements in reinforcement learning have made significant impacts across various domains, yet they often struggle in complex multi-agent environments due to issues like algorithm instability, low sampling efficiency, and the challenges of exploration and dimensionality explosion. Hierarchical reinforcement learning (HRL) offers a structured approach to decompose complex tasks into simpler sub-tasks, which is promising for multi-agent settings. This paper advances the field by introducing a hierarchical architecture that autonomously generates effective subgoals without explicit constraints, enhancing both flexibility and stability in training. We propose a dynamic goal generation strategy that adapts based on environmental changes. This method significantly improves the adaptability and sample efficiency of the learning process. Furthermore, we address the critical issue of credit assignment in multi-agent systems by synergizing our hierarchical architecture with a modified QMIX network, thus improving overall strategy coordination and efficiency. Comparative experiments with mainstream reinforcement learning algorithms demonstrate the superior convergence speed and performance of our approach in both single-agent and multi-agent environments, confirming its effectiveness and flexibility in complex scenarios. Our code is open-sourced at: \url{https://github.com/SICC-Group/GMAH}.

This technical report presents the Drama Engine, a novel framework for agentic interaction with large language models designed for narrative purposes. The framework adapts multi-agent system principles to create dynamic, context-aware companions that can develop over time and interact with users and each other. Key features include multi-agent workflows with delegation, dynamic prompt assembly, and model-agnostic design. The Drama Engine introduces unique elements such as companion development, mood systems, and automatic context summarising. It is implemented in TypeScript. The framework's applications include multi-agent chats and virtual co-workers for creative writing. The paper discusses the system's architecture, prompt assembly process, delegation mechanisms, and moderation techniques, as well as potential ethical considerations and future extensions.

This study addresses the challenge of fleet design optimization in the context of heterogeneous multi-robot fleets, aiming to obtain feasible designs that balance performance and costs. In the domain of autonomous multi-robot exploration, reinforcement learning agents play a central role, offering adaptability to complex terrains and facilitating collaboration among robots. However, modifying the fleet composition results in changes in the learned behavior, and training multi-robot systems using multi-agent reinforcement learning is expensive. Therefore, an exhaustive evaluation of each potential fleet design is infeasible. To tackle these hurdles, we introduce Bayesian Optimization for Fleet Design (BOFD), a framework leveraging multi-objective Bayesian Optimization to explore fleets on the Pareto front of performance and cost while accounting for uncertainty in the design space. Moreover, we establish a sub-linear bound for cumulative regret, supporting BOFD's robustness and efficacy. Extensive benchmark experiments in synthetic and simulated environments demonstrate the superiority of our framework over state-of-the-art methods, achieving efficient fleet designs with minimal fleet evaluations.

Recent works have provided algorithms by which decentralised agents, which may be connected via a communication network, can learn equilibria in Mean-Field Games from a single, non-episodic run of the empirical system. However, these algorithms are given for tabular settings: this computationally limits the size of players' observation space, meaning that the algorithms are not able to handle anything but small state spaces, nor to generalise beyond policies depending on the ego player's state to so-called 'population-dependent' policies. We address this limitation by introducing function approximation to the existing setting, drawing on the Munchausen Online Mirror Descent method that has previously been employed only in finite-horizon, episodic, centralised settings. While this permits us to include the population's mean-field distribution in the observation for each player's policy, it is arguably unrealistic to assume that decentralised agents would have access to this global information: we therefore additionally provide new algorithms that allow agents to estimate the global empirical distribution based on a local neighbourhood, and to improve this estimate via communication over a given network. Our experiments showcase how the communication network allows decentralised agents to estimate the mean-field distribution for population-dependent policies, and that exchanging policy information helps networked agents to outperform both independent and even centralised agents in function-approximation settings, by an even greater margin than in tabular settings.

How do people understand and evaluate claims about others' beliefs, even though these beliefs cannot be directly observed? In this paper, we introduce a cognitive model of epistemic language interpretation, grounded in Bayesian inferences about other agents' goals, beliefs, and intentions: a language-augmented Bayesian theory-of-mind (LaBToM). By translating natural language into an epistemic ``language-of-thought'', then evaluating these translations against the inferences produced by inverting a probabilistic generative model of rational action and perception, LaBToM captures graded plausibility judgments about epistemic claims. We validate our model in an experiment where participants watch an agent navigate a maze to find keys hidden in boxes needed to reach their goal, then rate sentences about the agent's beliefs. In contrast with multimodal LLMs (GPT-4o, Gemini Pro) and ablated models, our model correlates highly with human judgments for a wide range of expressions, including modal language, uncertainty expressions, knowledge claims, likelihood comparisons, and attributions of false belief.

We present an agent-based simulator for economic systems with heterogeneous households, firms, central bank, and government agents. These agents interact to define production, consumption, and monetary flow. Each agent type has distinct objectives, such as households seeking utility from consumption and the central bank targeting inflation and production. We define this multi-agent economic system using an OpenAI Gym-style environment, enabling agents to optimize their objectives through reinforcement learning. Standard multi-agent reinforcement learning (MARL) schemes, like independent learning, enable agents to learn concurrently but do not address whether the resulting strategies are at equilibrium. This study integrates the Policy Space Response Oracle (PSRO) algorithm, which has shown superior performance over independent MARL in games with homogeneous agents, with economic agent-based modeling. We use PSRO to develop agent policies approximating Nash equilibria of the empirical economic game, thereby linking to economic equilibria. Our results demonstrate that PSRO strategies achieve lower regret values than independent MARL strategies in our economic system with four agent types. This work aims to bridge artificial intelligence, economics, and empirical game theory towards future research.

A Viral Infection Risk Indoor Simulator (VIRIS) has been developed to quickly assess and compare mitigations for airborne disease spread. This agent-based simulator combines people movement in an indoor space, viral transmission modelling and detailed architectural design, and it is powered by topologicpy, an open-source Python library. VIRIS generates very fast predictions of the viral concentration and the spatiotemporal infection risk for individuals as they move through a given space. The simulator is validated with data from a courtroom superspreader event. A sensitivity study for unknown parameter values is also performed. We compare several non-pharmaceutical interventions (NPIs) issued in UK government guidance, for two indoor settings: a care home and a supermarket. Additionally, we have developed the user-friendly VIRIS web app that allows quick exploration of diverse scenarios of interest and visualisation, allowing policymakers, architects and space managers to easily design or assess infection risk in an indoor space.

Users of shared control systems change their behavior in the presence of assistance, which conflicts with assumpts about user behavior that some assistance methods make. In this paper, we propose an analysis technique to evaluate the user's experience with the assistive systems that bypasses required assumptions: we model the assistance as a dynamical system that can be analyzed using control theory techniques. We analyze the shared autonomy assistance algorithm and make several observations: we identify a problem with runaway goal confidence and propose a system adjustment to mitigate it, we demonstrate that the system inherently limits the possible actions available to the user, and we show that in a simplified setting, the effect of the assistance is to drive the system to the convex hull of the goals and, once there, add a layer of indirection between the user control and the system behavior. We conclude by discussing the possible uses of this analysis for the field.

The IR and information science communities have long studied tasks in search26 and many information-seeking models consider the role of tasks directly.3,11 Prior research has explored the different stages of task execution (for example, pre-focus, focus formation, post-focus), task levels, task facets, tasks defined on intents (for example, informational, transactional, and navigational; well-defined or ill-defined; and lookup, learn, or investigate), the hierarchical structure of tasks, the characteristics of tasks, the attributes of task-searcher interaction (for example, task difficulty), and, a focus of this article, task complexity.8 As a useful framing device to help conceptualize tasks and develop system support for them, tasks can be represented as trees comprising macrotasks (high-level goals), subtasks (specific components of those goals), and actions (specific steps taken by searchers toward the completion of those components).26 Figure 1 presents an example of a "task tree" for a task involving an upcoming vacation to Paris. Included are examples of macrotasks, subtasks, and actions.

Coordination of multi-robot systems (MRSs) relies on efficient sensing and reliable communication among the robots. However, the sensors and communication channels of these robots are often vulnerable to cyberattacks and faults, which can disrupt their individual behavior and the overall objective of the MRS. In this work, we present a multi-robot integrity monitoring framework that utilizes inter-robot range measurements to (i) detect the presence of cyberattacks or faults affecting the MRS, (ii) identify the affected robot(s), and (iii) reconstruct the resulting localization error of these robot(s). The proposed iterative algorithm leverages sequential convex programming and alternating direction of multipliers method to enable real-time and distributed implementation. Our approach is validated using numerical simulations and demonstrated using PX4-SiTL in Gazebo on an MRS, where certain agents deviate from their desired position due to a GNSS spoofing attack. Furthermore, we demonstrate the scalability and interoperability of our algorithm through mixed-reality experiments by forming a heterogeneous MRS comprising real Crazyflie UAVs and virtual PX4-SiTL UAVs working in tandem.