Federated embodied agent learning protects the data privacy of individual visual environments by keeping data locally at each client (the individual environment) during training. However, since the local data is inaccessible to the server under federated learning, attackers may easily poison the training data of the local client to build a backdoor in the agent without notice. Deploying such an agent raises the risk of potential harm to humans, as the attackers may easily navigate and control the agent as they wish via the backdoor. Towards Byzantine-robust federated embodied agent learning, in this paper, we study the attack and defense for the task of vision-and-language navigation (VLN), where the agent is required to follow natural language instructions to navigate indoor environments. First, we introduce a simple but effective attack strategy, Navigation as Wish (NAW), in which the malicious client manipulates local trajectory data to implant a backdoor into the global model. Results on two VLN datasets (R2R and RxR) show that NAW can easily navigate the deployed VLN agent regardless of the language instruction, without affecting its performance on normal test sets. Then, we propose a new Prompt-Based Aggregation (PBA) to defend against the NAW attack in federated VLN, which provides the server with a ''prompt'' of the vision-and-language alignment variance between the benign and malicious clients so that they can be distinguished during training. We validate the effectiveness of the PBA method on protecting the global model from the NAW attack, which outperforms other state-of-the-art defense methods by a large margin in the defense metrics on R2R and RxR.

The adaptive social learning paradigm helps model how networked agents are able to form opinions on a state of nature and track its drifts in a changing environment. In this framework, the agents repeatedly update their beliefs based on private observations and exchange the beliefs with their neighbors. In this work, it is shown how the sequence of publicly exchanged beliefs over time allows users to discover rich information about the underlying network topology and about the flow of information over the graph. In particular, it is shown that it is possible (i) to identify the influence of each individual agent to the objective of truth learning, (ii) to discover how well-informed each agent is, (iii) to quantify the pairwise influences between agents, and (iv) to learn the underlying network topology. The algorithm derived herein is also able to work under non-stationary environments where either the true state of nature or the graph topology are allowed to drift over time. We apply the proposed algorithm to different subnetworks of Twitter users, and identify the most influential and central agents by using their public tweets (posts).

Risky and crowded environments (RCE) contain abstract sources of risk and uncertainty, which are perceived differently by humans, leading to a variety of behaviors. Thus, robots deployed in RCEs, need to exhibit diverse perception and planning capabilities in order to interpret other human agents' behavior and act accordingly in such environments. To understand this problem domain, we conducted a study to explore human path choices in RCEs, enabling better robotic navigational explainable AI (XAI) designs. We created a novel COVID-19 pandemic grocery shopping scenario which had time-risk tradeoffs, and acquired users' path preferences. We found that participants showcase a variety of path preferences: from risky and urgent to safe and relaxed. To model users' decision making, we evaluated three popular risk models (Cumulative Prospect Theory (CPT), Conditional Value at Risk (CVAR), and Expected Risk (ER). We found that CPT captured people's decision making more accurately than CVaR and ER, corroborating theoretical results that CPT is more expressive and inclusive than CVaR and ER. We also found that people's self assessments of risk and time-urgency do not correlate with their path preferences in RCEs. Finally, we conducted thematic analysis of open-ended questions, providing crucial design insights for robots is RCE. Thus, through this study, we provide novel and critical insights about human behavior and perception to help design better navigational explainable AI (XAI) in RCEs.

Utilizing vehicle-to-everything (V2X) communication technologies, vehicle platooning systems are expected to realize a new paradigm of cooperative driving with higher levels of traffic safety and efficiency. Connected and Autonomous Vehicles (CAVs) need to have proper awareness of the traffic context. However, as the quantity of interconnected entities grows, the expense of communication will become a significant factor. As a result, the cooperative platoon's performance will be influenced by the communication strategy. While maintaining desired levels of performance, periodic communication can be relaxed to more flexible aperiodic or event-triggered implementations. In this paper, we propose a control-aware communication solution for vehicle platoons. The method uses a fully distributed control-aware communication strategy, attempting to decrease the usage of communication resources while still preserving the desired closed-loop performance characteristics. We then leverage Model-Based Communication (MBC) to improve cooperative vehicle perception in non-ideal communication and propose a solution that combines control-aware communication with MBC for cooperative control of vehicle platoons. Our approach achieves a significant reduction in the average communication rate ($47\%$) while only slightly reducing control performance (e.g., less than $1\%$ speed deviation). Through extensive simulations, we demonstrate the benefits of combined control-aware communication with MBC for cooperative control of vehicle platoons.

In cooperative multi-agent robotic systems, coordination is necessary in order to complete a given task. Important examples include search and rescue, operations in hazardous environments, and environmental monitoring. Coordination, in turn, requires simultaneous satisfaction of safety critical constraints, in the form of state and input constraints, and a connectivity constraint, in order to ensure that at every time instant there exists a communication path between every pair of agents in the network. In this work, we present a model predictive controller that tackles the problem of performing multi-agent coordination while simultaneously satisfying safety critical and connectivity constraints. The former is formulated in the form of state and input constraints and the latter as a constraint on the second smallest eigenvalue of the associated communication graph Laplacian matrix, also known as Fiedler eigenvalue, which enforces the connectivity of the communication network. We propose a sequential quadratic programming formulation to solve the associated optimization problem that is amenable to distributed optimization, making the proposed solution suitable for control of multi-agent robotics systems relying on local computation. Finally, the effectiveness of the algorithm is highlighted with a numerical simulation.

A central design problem in game theoretic analysis is the estimation of the players' utilities. In many real-world interactive situations of human decision making, including human driving, the utilities are multi-objective in nature; therefore, estimating the parameters of aggregation, i.e., mapping of multi-objective utilities to a scalar value, becomes an essential part of game construction. However, estimating this parameter from observational data introduces several challenges due to a host of unobservable factors, including the underlying modality of aggregation and the possibly boundedly rational behaviour model that generated the observation. Based on the concept of rationalisability, we develop algorithms for estimating multi-objective aggregation parameters for two common aggregation methods, weighted and satisficing aggregation, and for both strategic and non-strategic reasoning models. Based on three different datasets, we provide insights into how human drivers aggregate the utilities of safety and progress, as well as the situational dependence of the aggregation process. Additionally, we show that irrespective of the specific solution concept used for solving the games, a data-driven estimation of utility aggregation significantly improves the predictive accuracy of behaviour models with respect to observed human behaviour.

Detecting successful behaviour is crucial for training intelligent agents. As such, generalisable reward models are a prerequisite for agents that can learn to generalise their behaviour. In this work we focus on developing robust success detectors that leverage large, pretrained vision-language models (Flamingo, Alayrac et al. (2022)) and human reward annotations. Concretely, we treat success detection as a visual question answering (VQA) problem, denoted SuccessVQA. We study success detection across three vastly different domains: (i) interactive language-conditioned agents in a simulated household, (ii) real world robotic manipulation, and (iii) "in-the-wild" human egocentric videos. We investigate the generalisation properties of a Flamingo-based success detection model across unseen language and visual changes in the first two domains, and find that the proposed method is able to outperform bespoke reward models in out-of-distribution test scenarios with either variation. In the last domain of "in-the-wild" human videos, we show that success detection on unseen real videos presents an even more challenging generalisation task warranting future work. We hope our initial results encourage further work in real world success detection and reward modelling.

Value Decomposition (VD) aims to deduce the contributions of agents for decentralized policies in the presence of only global rewards, and has recently emerged as a powerful credit assignment paradigm for tackling cooperative Multi-Agent Reinforcement Learning (MARL) problems. One of the main challenges in VD is to promote diverse behaviors among agents, while existing methods directly encourage the diversity of learned agent networks with various strategies. However, we argue that these dedicated designs for agent networks are still limited by the indistinguishable VD network, leading to homogeneous agent behaviors and thus downgrading the cooperation capability. In this paper, we propose a novel Contrastive Identity-Aware learning (CIA) method, explicitly boosting the credit-level distinguishability of the VD network to break the bottleneck of multi-agent diversity. Specifically, our approach leverages contrastive learning to maximize the mutual information between the temporal credits and identity representations of different agents, encouraging the full expressiveness of credit assignment and further the emergence of individualities. The algorithm implementation of the proposed CIA module is simple yet effective that can be readily incorporated into various VD architectures. Experiments on the SMAC benchmarks and across different VD backbones demonstrate that the proposed method yields results superior to the state-of-the-art counterparts. Our code is available at https://github.com/liushunyu/CIA.

Although the field of multi-agent reinforcement learning (MARL) has made considerable progress in the last years, solving systems with a large number of agents remains a hard challenge. Graphon mean field games (GMFGs) enable the scalable analysis of MARL problems that are otherwise intractable. By the mathematical structure of graphons, this approach is limited to dense graphs which are insufficient to describe many real-world networks such as power law graphs. Our paper introduces a novel formulation of GMFGs, called LPGMFGs, which leverages the graph theoretical concept of $L^p$ graphons and provides a machine learning tool to efficiently and accurately approximate solutions for sparse network problems. This especially includes power law networks which are empirically observed in various application areas and cannot be captured by standard graphons. We derive theoretical existence and convergence guarantees and give empirical examples that demonstrate the accuracy of our learning approach for systems with many agents. Furthermore, we extend the Online Mirror Descent (OMD) learning algorithm to our setup to accelerate learning speed, empirically show its capabilities, and conduct a theoretical analysis using the novel concept of smoothed step graphons. In general, we provide a scalable, mathematically well-founded machine learning approach to a large class of otherwise intractable problems of great relevance in numerous research fields.

Existing multi-agent perception systems assume that every agent utilizes the same model with identical parameters and architecture. The performance can be degraded with different perception models due to the mismatch in their confidence scores. In this work, we propose a model-agnostic multi-agent perception framework to reduce the negative effect caused by the model discrepancies without sharing the model information. Specifically, we propose a confidence calibrator that can eliminate the prediction confidence score bias. Each agent performs such calibration independently on a standard public database to protect intellectual property. We also propose a corresponding bounding box aggregation algorithm that considers the confidence scores and the spatial agreement of neighboring boxes. Our experiments shed light on the necessity of model calibration across different agents, and the results show that the proposed framework improves the baseline 3D object detection performance of heterogeneous agents.