The recent rise in increasingly sophisticated cyber-attacks raises the need for robust and resilient autonomous cyber-defence (ACD) agents. Given the variety of cyber-attack tactics, techniques and procedures (TTPs) employed, learning approaches that can return generalisable policies are desirable. Meanwhile, the assurance of ACD agents remains an open challenge. We address both challenges via an empirical game-theoretic analysis of deep reinforcement learning (DRL) approaches for ACD using the principled double oracle (DO) algorithm. This algorithm relies on adversaries iteratively learning (approximate) best responses against each others' policies; a computationally expensive endeavour for autonomous cyber operations agents. In this work we introduce and evaluate a theoretically-sound, potential-based reward shaping approach to expedite this process. In addition, given the increasing number of open-source ACD-DRL approaches, we extend the DO formulation to allow for multiple response oracles (MRO), providing a framework for a holistic evaluation of ACD approaches.

The increasing complexity of modern software systems necessitates robust autonomic self-management capabilities. While Large Language Models (LLMs) demonstrate potential in this domain, they often face challenges in adapting their general knowledge to specific service contexts. To address this limitation, we propose ServiceOdyssey, a self-learning agent system that autonomously manages microservices without requiring prior knowledge of service-specific configurations. By leveraging curriculum learning principles and iterative exploration, ServiceOdyssey progressively develops a deep understanding of operational environments, reducing dependence on human input or static documentation. A prototype built with the Sock Shop microservice demonstrates the potential of this approach for autonomic microservice management.

Chemical language models for molecular design have the potential to find solutions to multi-parameter optimization problems in drug discovery via reinforcement learning (RL). A key requirement to achieve this is the capacity to "search" chemical space to identify all molecules of interest. Here, we propose a challenging new benchmark to discover dissimilar molecules that possess similar bioactivity, a common scenario in drug discovery, but a hard problem to optimize. We show that a population of RL agents can solve the benchmark, while a single agent cannot. We also find that cooperative strategies are not significantly better than independent agents. Moreover, the performance on the benchmark scales log-linearly with the number of independent agents, showing a test-time training scaling law for chemical language models.

Explanation is a fundamentally human process. Understanding the goal and audience of the explanation is vital, yet existing work on explainable reinforcement learning (XRL) routinely does not consult humans in their evaluations. Even when they do, they routinely resort to subjective metrics, such as confidence or understanding, that can only inform researchers of users' opinions, not their practical effectiveness for a given problem. This paper calls on researchers to use objective human metrics for explanation evaluations based on observable and actionable behaviour to build more reproducible, comparable, and epistemically grounded research. To this end, we curate, describe, and compare several objective evaluation methodologies for applying explanations to debugging agent behaviour and supporting human-agent teaming, illustrating our proposed methods using a novel grid-based environment. We discuss how subjective and objective metrics complement each other to provide holistic validation and how future work needs to utilise standardised benchmarks for testing to enable greater comparisons between research.

Inferring reward functions from demonstrations is a key challenge in reinforcement learning (RL), particularly in multi-agent RL (MARL), where large joint state-action spaces and complex inter-agent interactions complicate the task. While prior single-agent studies have explored recovering reward functions and policies from human preferences, similar work in MARL is limited. Existing methods often involve separate stages of supervised reward learning and MARL algorithms, leading to unstable training. In this work, we introduce a novel end-to-end preference-based learning framework for cooperative MARL, leveraging the underlying connection between reward functions and soft Q-functions. Our approach uses a carefully-designed multi-agent value decomposition strategy to improve training efficiency. Extensive experiments on SMAC and MAMuJoCo benchmarks show that our algorithm outperforms existing methods across various tasks.

Coordination behavior in robot swarms is inherently multi-modal in nature. That is, there are numerous ways in which a swarm of robots can avoid inter-agent collisions and reach their respective goals. However, the problem of generating diverse and feasible swarm behaviors in a scalable manner remains largely unaddressed. In this paper, we fill this gap by combining generative models with a safety-filter (SF). Specifically, we sample diverse trajectories from a learned generative model which is subsequently projected onto the feasible set using the SF. We experiment with two choices for generative models, namely: Conditional Variational Autoencoder (CVAE) and Vector-Quantized Variational Autoencoder (VQ-VAE). We highlight the trade-offs these two models provide in terms of computation time and trajectory diversity. We develop a custom solver for our SF and equip it with a neural network that predicts context-specific initialization. Thecinitialization network is trained in a self-supervised manner, taking advantage of the differentiability of the SF solver. We provide two sets of empirical results. First, we demonstrate that we can generate a large set of multi-modal, feasible trajectories, simulating diverse swarm behaviors, within a few tens of milliseconds. Second, we show that our initialization network provides faster convergence of our SF solver vis-a-vis other alternative heuristics.

We study decentralized multi-agent multi-armed bandits in fully heavy-tailed settings, where clients communicate over sparse random graphs with heavy-tailed degree distributions and observe heavy-tailed (homogeneous or heterogeneous) reward distributions with potentially infinite variance. The objective is to maximize system performance by pulling the globally optimal arm with the highest global reward mean across all clients. We are the first to address such fully heavy-tailed scenarios, which capture the dynamics and challenges in communication and inference among multiple clients in real-world systems. In homogeneous settings, our algorithmic framework exploits hub-like structures unique to heavy-tailed graphs, allowing clients to aggregate rewards and reduce noises via hub estimators when constructing UCB indices; under $M$ clients and degree distributions with power-law index $\alpha > 1$, our algorithm attains a regret bound (almost) of order $O(M^{1 -\frac{1}{\alpha}} \log{T})$. Under heterogeneous rewards, clients synchronize by communicating with neighbors, aggregating exchanged estimators in UCB indices; With our newly established information delay bounds on sparse random graphs, we prove a regret bound of $O(M \log{T})$. Our results improve upon existing work, which only address time-invariant connected graphs, or light-tailed dynamics in dense graphs and rewards.

Despite living in an increasingly connected world, social isolation is a prevalent issue today. While social robots have been explored as tools to enhance social connection through companionship, their potential as asynchronous social platforms for fostering connection towards humanity has received less attention. In this work, we introduce the design of a social support companion that facilitates the exchange of emotionally relevant stories and scaffolds reflection to enhance feelings of connection via five design dimensions. We investigate how social robots can serve as "social proxies" facilitating human stories, passing stories from other human narrators to the user. To this end, we conduct a real-world deployment of 40 robot stations in users' homes over the course of two weeks. Through thematic analysis of user interviews, we find that social proxy robots can foster connection towards other people's experiences via mechanisms such as identifying connections across stories or offering diverse perspectives. We present design guidelines from our study insights on the use of social robot systems that serve as social platforms to enhance human empathy and connection.

In contrast to classes of neural networks where the learned representations become increasingly expressive with network depth, the learned representations in graph neural networks (GNNs), tend to become increasingly similar. This phenomena, known as oversmoothing, is characterized by learned representations that cannot be reliably differentiated leading to reduced predictive performance. In this paper, we propose an analogy between oversmoothing in GNNs and consensus or agreement in opinion dynamics. Through this analogy, we show that the message passing structure of recent continuous-depth GNNs is equivalent to a special case of opinion dynamics (i.e., linear consensus models) which has been theoretically proven to converge to consensus (i.e., oversmoothing) for all inputs. Using the understanding developed through this analogy, we design a new continuous-depth GNN model based on nonlinear opinion dynamics and prove that our model, which we call behavior-inspired message passing neural network (BIMP) circumvents oversmoothing for general inputs. Through extensive experiments, we show that BIMP is robust to oversmoothing and adversarial attack, and consistently outperforms competitive baselines on numerous benchmarks.

The ever-approaching limits of the Earth's biosphere and the potentially catastrophic consequences caused by climate change have begun to call into question the endless growth of the economy. There is increasing interest in the prospects of zero economic growth from the degrowth and post-growth literature. In particular, the question arises as to whether a zero-growth trajectory in a capitalist system with interest-bearing debt can be economically stable. There have been several answers to this question using macroeconomic models; some find a zero-growth trajectory is stable, while other models show an economic breakdown. However, the capitalist system in a period of growth is not guaranteed to be stable. Hence, a more appropriate methodology is to compare the relative stability between a growth and zero-growth scenario on the same model. Such a question has not yet been answered at any disaggregated level. It's important to investigate the consequences of zero-growth on market share instability and concentration, bankruptcy rates, income distribution, and credit network risk. To answer such questions, we develop a macroeconomic agent-based model incorporating Minskyan financial dynamics. The growth and zero-growth scenarios are accomplished by changing an average productivity growth parameter for the firms in the model. The model results showed that real GDP growth rates were more stable in the zero-growth scenario, there were fewer economic crises, lower unemployment rates, a higher wage share of output for workers, and capital firm and bank market shares were relatively more stable. Some of the consequences of zero-growth were a higher rate of inflation than in the growth scenario, increased market concentration for both firms and banks, and a higher level of financial risk in the credit network.