This paper addresses the pursuit-evasion problem involving three agents -- a purser, an evader, and a defender. We develop cooperative guidance laws for the evader-defender team that guarantee that the defender intercepts the pursuer before it reaches the vicinity of the evader. Unlike heuristic methods, optimal control, differential game formulation, and recently proposed time-constrained guidance techniques, we propose a geometric solution to safeguard the evader from the pursuer's incoming threat. The proposed strategy is computationally efficient and expected to be scalable as the number of agents increases. Another alluring feature of the proposed strategy is that the evader-defender team does not require the knowledge of the pursuer's strategy and that the pursuer's interception is guaranteed from arbitrary initial engagement geometries. We further show that the necessary error variables for the evader-defender team vanish within a time that can be exactly prescribed prior to the three-body engagement. Finally, we demonstrate the efficacy of the proposed cooperative defense strategy via simulation in diverse engagement scenarios.

In the emerging space economy, autonomous robotic missions with specialized goals such as mapping and mining are gaining traction, with agencies and enterprises increasingly investing resources. Multirobot systems (MRS) research has provided many approaches to establish control and communication layers to facilitate collaboration from a technical perspective, such as granting more autonomy to heterogeneous robotic groups through auction-based interactions in mesh networks. However, stakeholders' competing economic interests often prevent them from cooperating within a proprietary ecosystem. Related work suggests that distributed ledger technology (DLT) might serve as a mechanism for enterprises to coordinate workflows and trade services to explore space resources through a transparent, reliable, non-proprietary digital platform. We challenge this perspective by pointing to the core technical weaknesses of blockchains, in particular, increased energy consumption, low throughput, and full transparency through redundancy. Our objective is to advance the discussion in a direction where the benefits of DLT from an economic perspective are weighted against the drawbacks from a technical perspective. We finally present a possible DLT-driven heterogeneous MRS for map exploration to study the opportunities for economic collaboration and competitiveness.

Graph Neural Networks (GNNs) have been a powerful tool for node classification tasks in complex networks. However, their decision-making processes remain a black-box to users, making it challenging to understand the reasoning behind their predictions. Counterfactual explanations (CFE) have shown promise in enhancing the interpretability of machine learning models. Prior approaches to compute CFE for GNNS often are learning-based approaches that require training additional graphs. In this paper, we propose a semivalue-based, non-learning approach to generate CFE for node classification tasks, eliminating the need for any additional training. Our results reveals that computing Banzhaf values requires lower sample complexity in identifying the counterfactual explanations compared to other popular methods such as computing Shapley values. Our empirical evidence indicates computing Banzhaf values can achieve up to a fourfold speed up compared to Shapley values. We also design a thresholding method for computing Banzhaf values and show theoretical and empirical results on its robustness in noisy environments, making it superior to Shapley values. Furthermore, the thresholded Banzhaf values are shown to enhance efficiency without compromising the quality (i.e., fidelity) in the explanations in three popular graph datasets.

In the new space economy, space agencies, large enterprises, and start-ups aim to launch space multi-robot systems (MRS) for various in-situ resource utilization (ISRU) purposes, such as mapping, soil evaluation, and utility provisioning. However, these stakeholders' competing economic interests may hinder effective collaboration on a centralized digital platform. To address this issue, neutral and transparent infrastructures could facilitate coordination and value exchange among heterogeneous space MRS. While related work has expressed legitimate concerns about the technical challenges associated with blockchain use in space, we argue that weighing its potential economic benefits against its drawbacks is necessary. This paper presents a novel architectural framework and a comprehensive set of requirements for integrating blockchain technology in MRS, aiming to enhance coordination and data integrity in space exploration missions. We explored distributed ledger technology (DLT) to design a non-proprietary architecture for heterogeneous MRS and validated the prototype in a simulated lunar environment. The analyses of our implementation suggest global ISRU efficiency improvements for map exploration, compared to a corresponding group of individually acting robots, and that fostering a coopetitive environment may provide additional revenue opportunities for stakeholders.

The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents across a wide range of domains, datasets, and tasks. Our training paradigm unifies diverse pre-training strategies, including visual masked auto-encoders, language modeling, and next-action prediction, enabling a versatile and adaptable AI framework. We demonstrate the performance of our framework across three separate domains -- Robotics, Gaming AI, and Healthcare. Our model demonstrates its ability to generate meaningful and contextually relevant outputs in each area. The strength of our approach lies in its generality, leveraging a variety of data sources such as robotics sequences, gameplay data, large-scale video datasets, and textual information for effective multimodal and multi-task learning. Our approach provides a promising avenue for developing generalist, action-taking, multimodal systems.

This work proposes a cooperative strategy that employs deviated pursuit guidance to simultaneously intercept a moving (but not manoeuvring) target. As opposed to many existing cooperative guidance strategies which use estimates of time-to-go, based on proportional-navigation guidance, the proposed strategy uses an exact expression for time-to-go to ensure simultaneous interception. The guidance design considers nonlinear engagement kinematics, allowing the proposed strategy to remain effective over a large operating regime. Unlike existing strategies on simultaneous interception that achieve interception at the average value of their initial time-to-go estimates, this work provides flexibility in the choice of impact time. By judiciously choosing the edge weights of the communication network, a weighted consensus in time-to-go can be achieved. It has been shown that by allowing an edge weight to be negative, consensus in time-to-go can even be achieved for an impact time that lies outside the convex hull of the set of initial time-to-go values of the individual interceptors. The bounds on such negative weights have been analysed for some special graphs, using Nyquist criterion. Simulations are provided to vindicate the efficacy of the proposed strategy.

Classical multi-agent reinforcement learning (MARL) assumes risk neutrality and complete objectivity for agents. However, in settings where agents need to consider or model human economic or social preferences, a notion of risk must be incorporated into the RL optimization problem. This will be of greater importance in MARL where other human or non-human agents are involved, possibly with their own risk-sensitive policies. In this work, we consider risk-sensitive and non-cooperative MARL with cumulative prospect theory (CPT), a non-convex risk measure and a generalization of coherent measures of risk. CPT is capable of explaining loss aversion in humans and their tendency to overestimate/underestimate small/large probabilities. We propose a distributed sampling-based actor-critic (AC) algorithm with CPT risk for network aggregative Markov games (NAMGs), which we call Distributed Nested CPT-AC. Under a set of assumptions, we prove the convergence of the algorithm to a subjective notion of Markov perfect Nash equilibrium in NAMGs. The experimental results show that subjective CPT policies obtained by our algorithm can be different from the risk-neutral ones, and agents with a higher loss aversion are more inclined to socially isolate themselves in an NAMG.

In fair division of a connected graph $G = (V, E)$, each of $n$ agents receives a share of $G$'s vertex set $V$. These shares partition $V$, with each share required to induce a connected subgraph. Agents use their own valuation functions to determine the non-negative numerical values of the shares, which determine whether the allocation is fair in some specified sense. We introduce forbidden substructures called graph cutsets, which block divisions that are fair in the EF1 (envy-free up to one item) sense by cutting the graph into "too many pieces". Two parameters - gap and valence - determine blocked values of $n$. If $G$ guarantees connected EF1 allocations for $n$ agents with valuations that are CA (common and additive), then $G$ contains no elementary cutset of gap $k \ge 2$ and valence in the interval $\[n - k + 1, n - 1\]$. If $G$ guarantees connected EF1 allocations for $n$ agents with valuations in the broader CM (common and monotone) class, then $G$ contains no cutset of gap $k \ge 2$ and valence in the interval $\[n - k + 1, n - 1\]$. These results rule out the existence of connected EF1 allocations in a variety of situations. For some graphs $G$ we can, with help from some new positive results, pin down $G$'s spectrum - the list of exactly which values of $n$ do/do not guarantee connected EF1 allocations. Examples suggest a conjectured common spectral pattern for all graphs. Further, we show that it is NP-hard to determine whether a graph admits a cutset. We also provide an example of a (non-traceable) graph on eight vertices that has no cutsets of gap $\ge 2$ at all, yet fails to guarantee connected EF1 allocations for three agents with CA preferences.

Offline RL (Levine et al., 2020), also known as batch RL, addresses the challenge of learning a near-optimal policy using offline datasets collected a priori, without further interactions with an environment. Fueled by the cost-effectiveness of utilizing pre-collected datasets compared to real-time explorations, offline RL has received increasing attention. However, the performance of offline RL crucially depends on the quality of offline datasets due to the lack of additional interactions with the environment, where the quality is determined by how thoroughly the state-action space is explored during data collection. Encouragingly, recent research (Li et al., 2022; Rashidinejad et al., 2021; Shi et al., 2022; Xie et al., 2021b) indicates that being more conservative on unseen state-action pairs, known as the principle of pessimism, enables learning of a near-optimal policy even with partial coverage of the state-action space, as long as the distribution of datasets encompasses the trajectory of the optimal policy. However, acquiring high-quality datasets that have good coverage of the optimal policy poses challenges because it requires the state-action visitation distribution induced by a behavior policy employed for data collection to be very close to the optimal policy. Alternatively, multiple datasets can be merged into one dataset to supplement insufficient coverage of one other, but this may be impractical when offline datasets are scattered and cannot be easily shared due to privacy and communication constraints.

There is increasing focus on adapting predictive models into agent-like systems, most notably AI assistants based on language models. We outline two structural reasons for why these models can fail when turned into agents. First, we discuss auto-suggestive delusions. Prior work has shown theoretically that models fail to imitate agents that generated the training data if the agents relied on hidden observations: the hidden observations act as confounding variables, and the models treat actions they generate as evidence for nonexistent observations. Second, we introduce and formally study a related, novel limitation: predictor-policy incoherence. When a model generates a sequence of actions, the model's implicit prediction of the policy that generated those actions can serve as a confounding variable. The result is that models choose actions as if they expect future actions to be suboptimal, causing them to be overly conservative. We show that both of those failures are fixed by including a feedback loop from the environment, that is, re-training the models on their own actions. We give simple demonstrations of both limitations using Decision Transformers and confirm that empirical results agree with our conceptual and formal analysis. Our treatment provides a unifying view of those failure modes, and informs the question of why fine-tuning offline learned policies with online learning makes them more effective.