Despite the prevalence of wireless connectivity in urban areas around the globe, there remain numerous and diverse situations where connectivity is insufficient or unavailable. To address this, we introduce mobile wireless infrastructure on demand, a system of UAVs that can be rapidly deployed to establish an ad-hoc wireless network. This network has the capability of reconfiguring itself dynamically to satisfy and maintain the required quality of communication. The system optimizes the positions of the UAVs and the routing of data flows throughout the network to achieve this quality of service (QoS). By these means, task agents using the network simply request a desired QoS, and the system adapts accordingly while allowing them to move freely. We have validated this system both in simulation and in real-world experiments. The results demonstrate that our system effectively offers mobile wireless infrastructure on demand, extending the operational range of task agents and supporting complex mobility patterns, all while ensuring connectivity and being resilient to agent failures.

The majority of Multi-Agent Reinforcement Learning (MARL) literature equates the cooperation of self-interested agents in mixed environments to the problem of social welfare maximization, allowing agents to arbitrarily share rewards and private information. This results in agents that forgo their individual goals in favour of social good, which can potentially be exploited by selfish defectors. We argue that cooperation also requires agents' identities and boundaries to be respected by making sure that the emergent behaviour is an equilibrium, i.e., a convention that no agent can deviate from and receive higher individual payoffs. Inspired by advances in mechanism design, we propose to solve the problem of cooperation, defined as finding socially beneficial equilibrium, by using mediators. A mediator is a benevolent entity that may act on behalf of agents, but only for the agents that agree to it. We show how a mediator can be trained alongside agents with policy gradient to maximize social welfare subject to constraints that encourage agents to cooperate through the mediator. Our experiments in matrix and iterative games highlight the potential power of applying mediators in MARL.

Semantic representation is a key enabler for several application domains, and the multi-agent systems realm makes no exception. Among the methods for semantically representing agents, one has been essentially achieved by taking a behaviouristic vision, through which one can describe how they operate and engage with their peers. The approach essentially aims at defining the operational capabilities of agents through the mental states related with the achievement of tasks. The OASIS ontology -- An Ontology for Agent, Systems, and Integration of Services, presented in 2019 -- pursues the behaviouristic approach to deliver a semantic representation system and a communication protocol for agents and their commitments. This paper reports on the main modeling choices concerning the representation of agents in OASIS 2, the latest major upgrade of OASIS, and the achievement reached by the ontology since it was first introduced, in particular in the context of ontologies for blockchains.

This paper presents a fully decentralized approach for realtime non-cooperative multi-robot navigation in social mini-games, such as navigating through a narrow doorway or negotiating right of way at a corridor intersection. Our contribution is a new realtime bi-level optimization algorithm, in which the top-level optimization consists of computing a fair and collision-free ordering followed by the bottom-level optimization which plans optimal trajectories conditioned on the ordering. We show that, given such a priority order, we can impose simple kinodynamic constraints on each robot that are sufficient for it to plan collision-free trajectories with minimal deviation from their preferred velocities, similar to how humans navigate in these scenarios. We successfully deploy the proposed algorithm in the real world using F$1/10$ robots, a Clearpath Jackal, and a Boston Dynamics Spot as well as in simulation using the SocialGym 2.0 multi-agent social navigation simulator, in the doorway and corridor intersection scenarios. We compare with state-of-the-art social navigation methods using multi-agent reinforcement learning, collision avoidance algorithms, and crowd simulation models. We show that $(i)$ classical navigation performs $44\%$ better than the state-of-the-art learning-based social navigation algorithms, $(ii)$ without a scheduling protocol, our approach results in collisions in social mini-games $(iii)$ our approach yields $2\times$ and $5\times$ fewer velocity changes than CADRL in doorways and intersections, and finally $(iv)$ bi-level navigation in doorways at a flow rate of $2.8 - 3.3$ (ms)$^{-1}$ is comparable to flow rate in human navigation at a flow rate of $4$ (ms)$^{-1}$.

Unmanned aerial vehicles (UAVs) serving as aerial base stations can be deployed to provide wireless connectivity to mobile users, such as vehicles. However, the density of vehicles on roads often varies spatially and temporally primarily due to mobility and traffic situations in a geographical area, making it difficult to provide ubiquitous service. Moreover, as energy-constrained UAVs hover in the sky while serving mobile users, they may be faced with interference from nearby UAV cells or other access points sharing the same frequency band, thereby impacting the system's energy efficiency (EE). Recent multi-agent reinforcement learning (MARL) approaches applied to optimise the users' coverage worked well in reasonably even densities but might not perform as well in uneven users' distribution, i.e., in urban road networks with uneven concentration of vehicles. In this work, we propose a density-aware communication-enabled multi-agent decentralised double deep Q-network (DACEMAD-DDQN) approach that maximises the total system's EE by jointly optimising the trajectory of each UAV, the number of connected users, and the UAVs' energy consumption while keeping track of dense and uneven users' distribution. Our result outperforms state-of-the-art MARL approaches in terms of EE by as much as 65% - 85%.

Rank aggregation is the problem of ordering a set of issues according to a set of individual rankings given as input. This problem has been studied extensively in computational social choice (see, e.g., Brandt et al. 2016) when the rankings are assumed to represent human preferences over, for example, candidates in a political election, projects to be funded, or more generally alternative proposals. The most common approach in this literature is to find normative desiderata for the aggregation process, including computational requirements such as the existence of tractable algorithms for its calculation and characterisations of the aggregators that satisfy them. Rank aggregation also has a wide spectrum of applications from metasearch engines [Dwork et al., 2001] to bioinformatics

Exploring sparse reward multi-agent reinforcement learning (MARL) environments with traps in a collaborative manner is a complex task. Agents typically fail to reach the goal state and fall into traps, which affects the overall performance of the system. To overcome this issue, we present SOMARL, a framework that uses prior knowledge to reduce the exploration space and assist learning. In SOMARL, agents are treated as part of the MARL environment, and symbolic knowledge is embedded using a tree structure to build a knowledge hierarchy. The framework has a two-layer hierarchical structure, comprising a hybrid module with a Hierarchical Task Network (HTN) planning and meta-controller at the higher level, and a MARL-based interactive module at the lower level. The HTN module and meta-controller use Hierarchical Domain Definition Language (HDDL) and the option framework to formalize symbolic knowledge and obtain domain knowledge and a symbolic option set, respectively. Moreover, the HTN module leverages domain knowledge to guide low-level agent exploration by assisting the meta-controller in selecting symbolic options. The meta-controller further computes intrinsic rewards of symbolic options to limit exploration behavior and adjust HTN planning solutions as needed. We evaluate SOMARL on two benchmarks, FindTreasure and MoveBox, and report superior performance over state-of-the-art MARL and subgoal-based baselines for MARL environments significantly.

MADDPG is an algorithm in multi-agent reinforcement learning (MARL) that extends the popular single-agent method, DDPG, to multi-agent scenarios. Importantly, DDPG is an algorithm designed for continuous action spaces, where the gradient of the state-action value function exists. For this algorithm to work in discrete action spaces, discrete gradient estimation must be performed. For MADDPG, the Gumbel-Softmax (GS) estimator is used -- a reparameterisation which relaxes a discrete distribution into a similar continuous one. This method, however, is statistically biased, and a recent MARL benchmarking paper suggests that this bias makes MADDPG perform poorly in grid-world situations, where the action space is discrete. Fortunately, many alternatives to the GS exist, boasting a wide range of properties. This paper explores several of these alternatives and integrates them into MADDPG for discrete grid-world scenarios. The corresponding impact on various performance metrics is then measured and analysed. It is found that one of the proposed estimators performs significantly better than the original GS in several tasks, achieving up to 55% higher returns, along with faster convergence.

Instruction-following agents must ground language into their observation and action spaces. Learning to ground language is challenging, typically requiring domain-specific engineering or large quantities of human interaction data. To address this challenge, we propose using pretrained vision-language models (VLMs) to supervise embodied agents. We combine ideas from model distillation and hindsight experience replay (HER), using a VLM to retroactively generate language describing the agent's behavior. Simple prompting allows us to control the supervision signal, teaching an agent to interact with novel objects based on their names (e.g., planes) or their features (e.g., colors) in a 3D rendered environment. Fewshot prompting lets us teach abstract category membership, including pre-existing categories (food vs toys) and ad-hoc ones (arbitrary preferences over objects). Our work outlines a new and effective way to use internet-scale VLMs, repurposing the generic language grounding acquired by such models to teach task-relevant groundings to embodied agents.

Robots operating alongside humans often encounter unfamiliar environments that make autonomous task completion challenging. Though improving models and increasing dataset size can enhance a robot's performance in unseen environments, dataset generation and model refinement may be impractical in every unfamiliar environment. Approaches that utilize human demonstration through manual operation can aid in generalizing to these unfamiliar environments, but often require significant human effort and expertise to achieve satisfactory task performance. To address these challenges, we propose leveraging part-time human interaction for redirection of robots during failed task execution. We train a lightweight help policy that allows robots to learn when to proceed autonomously or request human assistance at times of uncertainty. By incorporating part-time human intervention, robots recover quickly from their mistakes. Our best performing policy yields a 20 percent increase in path-length weighted success with only a 21 percent human interaction ratio. This approach provides a practical means for robots to interact and learn from humans in real-world settings, facilitating effective task completion without the need for significant human intervention.