Inspired by a graph-based technique for predicting molecular properties in quantum chemistry -- atoms' position within molecules in three-dimensional space -- we present Q-MARL, a completely decentralised learning architecture that supports very large-scale multi-agent reinforcement learning scenarios without the need for strong assumptions like common rewards or agent order. The key is to treat each agent as relative to its surrounding agents in an environment that is presumed to change dynamically. Hence, in each time step, an agent is the centre of its own neighbourhood and also a neighbour to many other agents. Each role is formulated as a sub-graph, and each sub-graph is used as a training sample. A message-passing neural network supports full-scale vertex and edge interaction within a local neighbourhood, while a parameter governing the depth of the sub-graphs eases the training burden. During testing, an agent's actions are locally ensembled across all the sub-graphs that contain it, resulting in robust decisions. Where other approaches struggle to manage 50 agents, Q-MARL can easily marshal thousands. A detailed theoretical analysis proves improvement and convergence, and simulations with the typical collaborative and competitive scenarios show dramatically faster training speeds and reduced training losses.

Abstract-- We introduce AttentionSwarm, a novel benchmark designed to evaluate safe and efficient swarm control across three challenging environments: a landing environment with obstacles, a competitive drone game setting, and a dynamic drone racing scenario. Central to our approach is the Attention Model Based Control Barrier Function (CBF) framework, which integrates attention mechanisms with safety-critical control theory to enable real-time collision avoidance and trajectory optimization. The safe attention net algorithm was developed and evaluated using a swarm of Crazyflie 2.1 micro quadrotors, which were tested indoors with the Vicon motion capture system to ensure precise localization and control. Experimental results show that our system achieves landing accuracy of 3.02 cm with a mean time of 23 s and collision-free landings in a dynamic landing environment, 100% and collision-free navigation in a drone game environment, and 95% and collision-free navigation for a dynamic multiagent drone racing environment, underscoring its effectiveness and robustness in real-world scenarios. In recent years, Deep Reinforcement Learning (DRL) has emerged as a critical methodology in robotics, driving advances in systems that require adaptability [1], [2], [3].

Prevailing top-down systems in politics and economics struggle to keep pace with the pressing challenges of the 21st century, such as climate change, social inequality and conflict. Bottom-up democratisation and participatory approaches in politics and economics are increasingly seen as promising alternatives to confront and overcome these issues, often with utopian overtones, as proponents believe they may dramatically reshape political, social and ecological futures for the better and in contrast to contemporary authoritarian tendencies across various countries. Institutional specifics and the associated collective human behavior or culture remains little understood and debated, however. In this article, I propose a novel research agenda focusing on utopian democratisation efforts with formal and computational methods as well as with artificial intelligence - I call this agenda Artificial Utopia. Artificial Utopias provide safe testing grounds for new political ideas and economic policies in-silico with reduced risk of negative consequences as compared to testing ideas in real-world contexts. An increasing number of advanced simulation and intelligence methods, that aim at representing human cognition and collective decision-making in more realistic ways, could benefit this process. This includes agent-based modelling, reinforcement learning, large language models and more. I clarify what some of these simulation approaches can contribute to the study of Artificial Utopias with the help of two institutional examples: the citizen assembly and the democratic firm.

In the field of robot target recognition research driven by artificial intelligence (AI), factors such as the disordered distribution of targets, the complexity of the environment, the massive scale of data, and noise interference have significantly restricted the improvement of target recognition accuracy. Against the backdrop of the continuous iteration and upgrading of current AI technologies, to meet the demand for accurate recognition of disordered targets by intelligent robots in complex and changeable scenarios, this study innovatively proposes an AI - based intelligent robot disordered target recognition method using reinforcement learning. This method processes the collected target images with the bilateral filtering algorithm, decomposing them into low - illumination images and reflection images. Subsequently, it adopts differentiated AI strategies, compressing the illumination images and enhancing the reflection images respectively, and then fuses the two parts of images to generate a new image. On this basis, this study deeply integrates deep learning, a core AI technology, with the reinforcement learning algorithm. The enhanced target images are input into a deep reinforcement learning model for training, ultimately enabling the AI - based intelligent robot to efficiently recognize disordered targets. Experimental results show that the proposed method can not only significantly improve the quality of target images but also enable the AI - based intelligent robot to complete the recognition task of disordered targets with higher efficiency and accuracy, demonstrating extremely high application value and broad development prospects in the field of AI robots.

The key to robot-assisted rehabilitation lies in the design of the human-machine interface, which must accommodate the needs of both patients and machines. Current interface designs primarily focus on machine control algorithms, often requiring patients to spend considerable time adapting. In this paper, we introduce a novel approach based on the Cooperative Adaptive Markov Decision Process (CAMDPs) model to address the fundamental aspects of the interactive learning process, offering theoretical insights and practical guidance. We establish sufficient conditions for the convergence of CAMDPs and ensure the uniqueness of Nash equilibrium points. Leveraging these conditions, we guarantee the system's convergence to a unique Nash equilibrium point. Furthermore, we explore scenarios with multiple Nash equilibrium points, devising strategies to adjust both Value Evaluation and Policy Improvement algorithms to enhance the likelihood of converging to the global minimal Nash equilibrium point. Through numerical experiments, we illustrate the effectiveness of the proposed conditions and algorithms, demonstrating their applicability and robustness in practical settings. The proposed conditions for convergence and the identification of a unique optimal Nash equilibrium contribute to the development of more effective adaptive systems for human users in robot-assisted rehabilitation.

Traditional rule-based decision-making methods with interpretable advantage, such as finite state machine, suffer from the jitter or deadlock(JoD) problems in extremely dynamic scenarios. To realize agent swarm confrontation, decision conflicts causing many JoD problems are a key issue to be solved. Here, we propose a novel decision-making framework that integrates probabilistic finite state machine, deep convolutional networks, and reinforcement learning to implement interpretable intelligence into agents. Our framework overcomes state machine instability and JoD problems, ensuring reliable and adaptable decisions in swarm confrontation. The proposed approach demonstrates effective performance via enhanced human-like cooperation and competitive strategies in the rigorous evaluation of real experiments, outperforming other methods.

The last few years have seen an explosion of interest in autonomous cyber defence agents based on deep reinforcement learning. Such agents are typically trained in a cyber gym environment, also known as a cyber simulator, at least 32 of which have already been built. Most, if not all cyber gyms provide dense "scaffolded" reward functions which combine many penalties or incentives for a range of (un)desirable states and costly actions. Whilst dense rewards help alleviate the challenge of exploring complex environments, yielding seemingly effective strategies from relatively few environment steps; they are also known to bias the solutions an agent can find, potentially towards suboptimal solutions. This is especially a problem in complex cyber environments where policy weaknesses may not be noticed until exploited by an adversary. In this work we set out to evaluate whether sparse reward functions might enable training more effective cyber defence agents. Towards this goal we first break down several evaluation limitations in existing work by proposing a ground truth evaluation score that goes beyond the standard RL paradigm used to train and evaluate agents. By adapting a well-established cyber gym to accommodate our methodology and ground truth score, we propose and evaluate two sparse reward mechanisms and compare them with a typical dense reward. Our evaluation considers a range of network sizes, from 2 to 50 nodes, and both reactive and proactive defensive actions. Our results show that sparse rewards, particularly positive reinforcement for an uncompromised network state, enable the training of more effective cyber defence agents. Furthermore, we show that sparse rewards provide more stable training than dense rewards, and that both effectiveness and training stability are robust to a variety of cyber environment considerations.

Humanoid robots, capable of assuming human roles in various workplaces, have become essential to the advancement of embodied intelligence. However, as robots with complex physical structures, learning a control model that can operate robustly across diverse environments remains inherently challenging, particularly under the discrepancies between training and deployment environments. In this study, we propose HWC-Loco, a robust whole-body control algorithm tailored for humanoid locomotion tasks. By reformulating policy learning as a robust optimization problem, HWC-Loco explicitly learns to recover from safety-critical scenarios. While prioritizing safety guarantees, overly conservative behavior can compromise the robot's ability to complete the given tasks. To tackle this challenge, HWC-Loco leverages a hierarchical policy for robust control. This policy can dynamically resolve the trade-off between goal-tracking and safety recovery, guided by human behavior norms and dynamic constraints. To evaluate the performance of HWC-Loco, we conduct extensive comparisons against state-of-the-art humanoid control models, demonstrating HWC-Loco's superior performance across diverse terrains, robot structures, and locomotion tasks under both simulated and real-world environments.

Domain Generalization (DG) research has gained considerable traction as of late, since the ability to generalize to unseen data distributions is a requirement that eludes even state-of-the-art training algorithms. In this paper we observe that the initial iterations of model training play a key role in domain generalization effectiveness, since the loss landscape may be significantly different across the training and test distributions, contrary to the case of i.i.d. data. Conflicts between gradients of the loss components of each domain lead the optimization procedure to undesirable local minima that do not capture the domain-invariant features of the target classes. We propose alleviating domain conflicts in model optimization, by iteratively annealing the parameters of a model in the early stages of training and searching for points where gradients align between domains. By discovering a set of parameter values where gradients are updated towards the same direction for each data distribution present in the training set, the proposed Gradient-Guided Annealing (GGA) algorithm encourages models to seek out minima that exhibit improved robustness against domain shifts. The efficacy of GGA is evaluated on five widely accepted and challenging image classification domain generalization benchmarks, where its use alone is able to establish highly competitive or even state-of-the-art performance. Moreover, when combined with previously proposed domain-generalization algorithms it is able to consistently improve their effectiveness by significant margins.

How can we build generalist robot systems? Scale may not be enough due to the significant multimodality of robotics tasks, lack of easily accessible data and the challenges of deploying on physical hardware. Meanwhile, most deployed robotic systems today are inherently modular and can leverage the independent generalization capabilities of each module to perform well. Therefore, this thesis seeks to tackle the task of building generalist robot agents by integrating these components into one: combining modularity with large-scale learning for general purpose robot control. The first question we consider is: how can we build modularity and hierarchy into learning systems? Our key insight is that rather than having the agent learn hierarchy and low-level control end-to-end, we can enforce modularity via planning to enable more efficient and capable robot learners. Next, we come to the role of scale in building generalist robot systems. To scale, neural networks require vast amounts of diverse data, expressive architectures to fit the data and a source of supervision to generate the data. We leverage a powerful supervision source: classical planning, which can generalize, but is expensive to run and requires access to privileged information to perform well in practice. We use these planners to supervise large-scale policy learning in simulation to produce generalist agents. Finally, we consider how to unify modularity with large-scale policy learning to build real-world robot systems capable of performing zero-shot manipulation. We do so by tightly integrating key ingredients of modular high and mid-level planning, learned local control, procedural scene generation and large-scale policy learning for sim2real transfer. We demonstrate that this recipe can produce a single, generalist agent that can solve challenging long-horizon manipulation tasks in the real world.