Consensus-based decentralized stochastic gradient descent (D-SGD) is a widely adopted algorithm for decentralized training of machine learning models across networked agents. A crucial part of D-SGD is the consensus-based model averaging, which heavily relies on information exchange and fusion among the nodes. Specifically, for consensus averaging over wireless networks, communication coordination is necessary to determine when and how a node can access the channel and transmit (or receive) information to (or from) its neighbors. In this work, we propose $\texttt{BASS}$, a broadcast-based subgraph sampling method designed to accelerate the convergence of D-SGD while considering the actual communication cost per iteration. $\texttt{BASS}$ creates a set of mixing matrix candidates that represent sparser subgraphs of the base topology. In each consensus iteration, one mixing matrix is sampled, leading to a specific scheduling decision that activates multiple collision-free subsets of nodes. The sampling occurs in a probabilistic manner, and the elements of the mixing matrices, along with their sampling probabilities, are jointly optimized. Simulation results demonstrate that $\texttt{BASS}$ enables faster convergence with fewer transmission slots compared to existing link-based scheduling methods. In conclusion, the inherent broadcasting nature of wireless channels offers intrinsic advantages in accelerating the convergence of decentralized optimization and learning.

Autonomous agents capable of planning, reasoning, and executing actions on the web offer a promising avenue for automating computer tasks. However, the majority of existing benchmarks primarily focus on text-based agents, neglecting many natural tasks that require visual information to effectively solve. Given that most computer interfaces cater to human perception, visual information often augments textual data in ways that text-only models struggle to harness effectively. To bridge this gap, we introduce VisualWebArena, a benchmark designed to assess the performance of multimodal web agents on realistic \textit{visually grounded tasks}. VisualWebArena comprises of a set of diverse and complex web-based tasks that evaluate various capabilities of autonomous multimodal agents. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives. We conduct an extensive evaluation of state-of-the-art LLM-based autonomous agents, including several multimodal models. Through extensive quantitative and qualitative analysis, we identify several limitations of text-only LLM agents, and reveal gaps in the capabilities of state-of-the-art multimodal language agents. VisualWebArena provides a framework for evaluating multimodal autonomous language agents, and offers insights towards building stronger autonomous agents for the web. Our code, baseline models, and data is publicly available at https://jykoh.com/vwa.

In this paper we propose a periodic solution to the problem of persistently covering a finite set of interest points with a group of autonomous mobile agents. These agents visit periodically the points and spend some time carrying out the coverage task, which we call coverage time. Since this periodic persistent coverage problem is NP-hard, we split it into three subproblems to counteract its complexity. In the first place, we plan individual closed paths for the agents to cover all the points. Second, we formulate a quadratically constrained linear program to find the optimal coverage times and actions that satisfy the coverage objective. Finally, we join together the individual plans of the agents in a periodic team plan by obtaining a schedule that guarantees collision avoidance. To this end, we solve a mixed integer linear program that minimizes the time in which two or more agents move at the same time. Eventually, we apply the proposed solution to an induction hob with mobile inductors for a domestic heating application and show its performance with experiments on a real prototype.

In this paper we tackle the problem of persistently covering a complex non-convex environment with a team of robots. We consider scenarios where the coverage quality of the environment deteriorates with time, requiring to constantly revisit every point. As a first step, our solution finds a partition of the environment where the amount of work for each robot, weighted by the importance of each point, is equal. This is achieved using a power diagram and finding an equitable partition through a provably correct distributed control law on the power weights. Compared to other existing partitioning methods, our solution considers a continuous environment formulation with non-convex obstacles. In the second step, each robot computes a graph that gathers sweep-like paths and covers its entire partition. At each planning time, the coverage error at the graph vertices is assigned as weights of the corresponding edges. Then, our solution is capable of efficiently finding the optimal open coverage path through the graph with respect to the coverage error per distance traversed. Simulation and experimental results are presented to support our proposal.

We consider a scenario of cooperative task servicing, with a team of heterogeneous robots with different maximum speeds and communication radii, in charge of keeping the network intermittently connected. We abstract the task locations into a $1D$ cycle graph that is traversed by the communicating robots, and we discuss intermittent communication strategies so that each task location is periodically visited, with a worst--case revisiting time. Robots move forward and backward along the cycle graph, exchanging data with their previous and next neighbors when they meet, and updating their region boundaries. Asymptotically, each robot is in charge of a region of the cycle graph, depending on its capabilities. The method is distributed, and robots only exchange data when they meet.

We present a novel vision-based control method to make a group of ground mobile robots achieve a specified formation shape with unspecified size. Our approach uses multiple aerial control units equipped with downward-facing cameras, each observing a partial subset of the multirobot team. The units compute the control commands from the ground robots' image projections, using neither calibration nor scene scale information, and transmit them to the robots. The control strategy relies on the calculation of image similarity transformations, and we show it to be asymptotically stable if the overlaps between the subsets of controlled robots satisfy certain conditions. The presence of the supervisory units, which coordinate their motions to guarantee a correct control performance, gives rise to a hybrid system topology. All in all, the proposed system provides relevant practical advantages in simplicity and flexibility. Within the problem of controlling a team shape, our contribution lies in addressing several simultaneous challenges: the controller needs only partial information of the robotic group, does not use distance measurements or global reference frames, is designed for unicycle agents, and can accommodate topology changes. We present illustrative simulation results.

Cognitive agent abstractions can help to engineer intelligent systems across mobile devices. On smartphones, the data obtained from onboard sensors can give valuable insights into the user's current situation. Unfortunately, today's cognitive agent frameworks cannot cope well with the challenging characteristics of sensor data. Sensor data is located on a low abstraction level and the individual data elements are not meaningful when observed in isolation. In contrast, cognitive agents operate on high-level percepts and lack the means to effectively detect complex spatio-temporal patterns in sequences of multiple percepts. In this paper, we present a stream-based perception approach that enables the agents to perceive meaningful situations in low-level sensor data streams. We present a crowdshipping case study where autonomous, self-interested agents collaborate to deliver parcels to their destinations. We show how situations derived from smartphone sensor data can trigger and guide auctions, which the agents use to reach agreements. Experiments with real smartphone data demonstrate the benefits of stream-based agent perception.

In the rapidly advancing field of multi-agent systems, ensuring robustness in unfamiliar and adversarial settings is crucial. Notwithstanding their outstanding performance in familiar environments, these systems often falter in new situations due to overfitting during the training phase. This is especially pronounced in settings where both cooperative and competitive behaviours are present, encapsulating a dual nature of overfitting and generalisation challenges. To address this issue, we present Multi-Agent Diagnostics for Robustness via Illuminated Diversity (MADRID), a novel approach for generating diverse adversarial scenarios that expose strategic vulnerabilities in pre-trained multi-agent policies. Leveraging the concepts from open-ended learning, MADRID navigates the vast space of adversarial settings, employing a target policy's regret to gauge the vulnerabilities of these settings. We evaluate the effectiveness of MADRID on the 11vs11 version of Google Research Football, one of the most complex environments for multi-agent reinforcement learning. Specifically, we employ MADRID for generating a diverse array of adversarial settings for TiZero, the state-of-the-art approach which "masters" the game through 45 days of training on a large-scale distributed infrastructure. We expose key shortcomings in TiZero's tactical decision-making, underlining the crucial importance of rigorous evaluation in multi-agent systems.

Blockchains deploy Transaction Fee Mechanisms (TFMs) to determine which user transactions to include in blocks and determine their payments (i.e., transaction fees). Increasing demand and scarce block resources have led to high user transaction fees. As these blockchains are a public resource, it may be preferable to reduce these transaction fees. To this end, we introduce Transaction Fee Redistribution Mechanisms (TFRMs) -- redistributing VCG payments collected from such TFM as rebates to minimize transaction fees. Classic redistribution mechanisms (RMs) achieve this while ensuring Allocative Efficiency (AE) and User Incentive Compatibility (UIC). Our first result shows the non-triviality of applying RM in TFMs. More concretely, we prove that it is impossible to reduce transaction fees when (i) transactions that are not confirmed do not receive rebates and (ii) the miner can strategically manipulate the mechanism. Driven by this, we propose \emph{Robust} TFRM (\textsf{R-TFRM}): a mechanism that compromises on an honest miner's individual rationality to guarantee strictly positive rebates to the users. We then introduce \emph{robust} and \emph{rational} TFRM (\textsf{R}$^2$\textsf{-TFRM}) that uses trusted on-chain randomness that additionally guarantees miner's individual rationality (in expectation) and strictly positive rebates. Our results show that TFRMs provide a promising new direction for reducing transaction fees in public blockchains.

This paper explores the integration of optimal transport (OT) theory with multi-agent reinforcement learning (MARL). This integration uses OT to handle distributions and transportation problems to enhance the efficiency, coordination, and adaptability of MARL. There are five key areas where OT can impact MARL: (1) policy alignment, where OT's Wasserstein metric is used to align divergent agent strategies towards unified goals; (2) distributed resource management, employing OT to optimize resource allocation among agents; (3) addressing non-stationarity, using OT to adapt to dynamic environmental shifts; (4) scalable multi-agent learning, harnessing OT for decomposing large-scale learning objectives into manageable tasks; and (5) enhancing energy efficiency, applying OT principles to develop sustainable MARL systems. This paper articulates how the synergy between OT and MARL can address scalability issues, optimize resource distribution, align agent policies in cooperative environments, and ensure adaptability in dynamically changing conditions.