A hub-based colony consists of multiple agents who share a common nest site called the hub. Agents perform tasks away from the hub like foraging for food or gathering information about future nest sites. Modeling hub-based colonies is challenging because the size of the collective state space grows rapidly as the number of agents grows. This paper presents a graph-based representation of the colony that can be combined with graph-based encoders to create low-dimensional representations of collective state that can scale to many agents for a best-of-N colony problem. We demonstrate how the information in the low-dimensional embedding can be used with two experiments. First, we show how the information in the tensor can be used to cluster collective states by the probability of choosing the best site for a very small problem. Second, we show how structured collective trajectories emerge when a graph encoder is used to learn the low-dimensional embedding, and these trajectories have information that can be used to predict swarm performance.

Multi-agent reinforcement learning (MARL) methods, while effective in zero-sum or positive-sum games, often yield suboptimal outcomes in general-sum games where cooperation is essential for achieving globally optimal outcomes. Matrix game social dilemmas, which abstract key aspects of general-sum interactions, such as cooperation, risk, and trust, fail to model the temporal and spatial dynamics characteristic of real-world scenarios. In response, our study extends matrix game social dilemmas into more complex, higher-dimensional MARL environments. We adapt a gridworld implementation of the Stag Hunt dilemma to more closely match the decision-space of a one-shot matrix game while also introducing variable environment complexity. Our findings indicate that as complexity increases, MARL agents trained in these environments converge to suboptimal strategies, consistent with the risk-dominant Nash equilibria strategies found in matrix games. Our work highlights the impact of environment complexity on achieving optimal outcomes in higher-dimensional game-theoretic MARL environments.

Emergent effects can arise in multi-agent systems (MAS) where execution is decentralized and reliant on local information. These effects may range from minor deviations in behavior to catastrophic system failures. To formally define these effects, we identify misalignments between the global inherent specification (the true specification) and its local approximation (such as the configuration of different reward components or observations). Using established safety terminology, we develop a framework to understand these emergent effects. To showcase the resulting implications, we use two broadly configurable exemplary gridworld scenarios, where insufficient specification leads to unintended behavior deviations when derived independently. Recognizing that a global adaptation might not always be feasible, we propose adjusting the underlying parameterizations to mitigate these issues, thereby improving the system's alignment and reducing the risk of emergent failures.

Smart autonomous agents are becoming increasingly important in various real-life applications, including robotics and autonomous vehicles. One crucial skill that these agents must possess is the ability to interact with their surrounding entities, such as other agents or humans. In this work, we aim at building an intelligent agent that can efficiently navigate in an environment while being able to interact with an oracle (or human) in natural language and ask for directions when it is unsure about its navigation performance. The interaction is started by the agent that produces a question, which is then answered by the oracle on the basis of the shortest trajectory to the goal. The process can be performed multiple times during navigation, thus enabling the agent to hold a dialogue with the oracle. To this end, we propose a novel computational model, named UNMuTe, that consists of two main components: a dialogue model and a navigator. Specifically, the dialogue model is based on a GPT-2 decoder that handles multimodal data consisting of both text and images. First, the dialogue model is trained to generate question-answer pairs: the question is generated using the current image, while the answer is produced leveraging future images on the path toward the goal. Subsequently, a VLN model is trained to follow the dialogue predicting navigation actions or triggering the dialogue model if it needs help. In our experimental analysis, we show that UNMuTe achieves state-of-the-art performance on the main navigation tasks implying dialogue, i.e. Cooperative Vision and Dialogue Navigation (CVDN) and Navigation from Dialogue History (NDH), proving that our approach is effective in generating useful questions and answers to guide navigation.

Altruistic cooperation is costly yet socially desirable. As a result, agents struggle to learn cooperative policies through independent reinforcement learning (RL). Indirect reciprocity, where agents consider their interaction partner's reputation, has been shown to stabilise cooperation in homogeneous, idealised populations. However, more realistic settings are comprised of heterogeneous agents with different characteristics and group-based social identities. We study cooperation when agents are stratified into two such groups, and allow reputation updates and actions to depend on group information. We consider two modelling approaches: evolutionary game theory, where we comprehensively search for social norms (i.e., rules to assign reputations) leading to cooperation and fairness; and RL, where we consider how the stochastic dynamics of policy learning affects the analytically identified equilibria. We observe that a defecting majority leads the minority group to defect, but not the inverse. Moreover, changing the norms that judge in and out-group interactions can steer a system towards either fair or unfair cooperation. This is made clearer when moving beyond equilibrium analysis to independent RL agents, where convergence to fair cooperation occurs with a narrower set of norms. Our results highlight that, in heterogeneous populations with reputations, carefully defining interaction norms is fundamental to tackle both dilemmas of cooperation and of fairness.

Digital agents are considered a general-purpose technology. They spread quickly in private and organizational contexts, including education. Yet, research lacks a conceptual framing to describe interaction with such agents in a holistic manner. While focusing on the interaction with a pedagogical agent, i.e., a digital agent capable of natural-language interaction with a learner, we propose a model of learning activity based on activity theory. We use this model and a review of prior research on digital agents in education to analyze how various characteristics of the activity, including features of a pedagogical agent or learner, influence learning outcomes. The analysis leads to identification of IS research directions and guidance for developers of pedagogical agents and digital agents in general. We conclude by extending the activity theory-based model beyond the context of education and show how it helps designers and researchers ask the right questions when creating a digital agent.

Multi-agent proximal policy optimization (MAPPO) has recently demonstrated state-of-the-art performance on challenging multi-agent reinforcement learning tasks. However, MAPPO still struggles with the credit assignment problem, wherein the sheer difficulty in ascribing credit to individual agents' actions scales poorly with team size. In this paper, we propose a multi-agent reinforcement learning algorithm that adapts recent developments in credit assignment to improve upon MAPPO. Our approach leverages partial reward decoupling (PRD), which uses a learned attention mechanism to estimate which of a particular agent's teammates are relevant to its learning updates. We use this estimate to dynamically decompose large groups of agents into smaller, more manageable subgroups. We empirically demonstrate that our approach, PRD-MAPPO, decouples agents from teammates that do not influence their expected future reward, thereby streamlining credit assignment. We additionally show that PRD-MAPPO yields significantly higher data efficiency and asymptotic performance compared to both MAPPO and other state-of-the-art methods across several multi-agent tasks, including StarCraft II. Finally, we propose a version of PRD-MAPPO that is applicable to \textit{shared} reward settings, where PRD was previously not applicable, and empirically show that this also leads to performance improvements over MAPPO.

In a typical e-commerce setting, Content Ranking Optimization (CRO) mechanisms are employed to surface content on the search page to fulfill customers' shopping missions. CRO commonly utilizes models such as contextual deep bandits model to independently rank content at different positions, e.g., one optimizer dedicated to organic search results and another to sponsored results. However, this regional optimization approach does not necessarily translate to whole page optimization, e.g., maximizing revenue at the top of the page may inadvertently diminish the revenue of lower positions. In this paper, we propose a reinforcement learning based method for whole page ranking to jointly optimize across all positions by: 1) shifting from position level optimization to whole page level optimization to achieve an overall optimized ranking; 2) applying reinforcement learning to optimize for the cumulative rewards instead of the instant reward. We formulate page level CRO as a cooperative Multi-agent Markov Decision Process , and address it with the novel Multi-Agent Deep Deterministic Policy Gradient (MADDPG) model. MADDPG supports a flexible and scalable joint optimization framework by adopting a "centralized training and decentralized execution" approach. Extensive experiments demonstrate that MADDPG scales to a 2.5 billion action space in the public Mujoco environment, and outperforms the deep bandits modeling by 25.7% on the offline CRO data set from a leading e-commerce company. We foresee that this novel multi-agent optimization is applicable to similar joint optimization problems in the field of information retrieval.

In this paper we explore the performance of deep hidden physics model (M. Raissi 2018) for autonomous systems. These systems are described by set of ordinary differential equations which do not explicitly depend on time. Such systems can be found in nature and have applications in modeling chemical concentrations, population dynamics, n-body problems in physics etc. In this work we consider dynamics of states, which explain how the states will evolve are unknown to us. We approximate state and dynamics both using neural networks. We have considered examples of 2D linear/nonlinear and Lorenz systems. We observe that even without knowing all the states information, we can estimate dynamics of certain states whose state information are known.

Credit assignment is a core problem that distinguishes agents' marginal contributions for optimizing cooperative strategies in multi-agent reinforcement learning (MARL). Current credit assignment methods usually assume synchronous decision-making among agents. However, a prerequisite for many realistic cooperative tasks is asynchronous decision-making by agents, without waiting for others to avoid disastrous consequences. To address this issue, we propose an asynchronous credit assignment framework with a problem model called ADEX-POMDP and a multiplicative value decomposition (MVD) algorithm. ADEX-POMDP is an asynchronous problem model with extra virtual agents for a decentralized partially observable markov decision process. We prove that ADEX-POMDP preserves both the task equilibrium and the algorithm convergence. MVD utilizes multiplicative interaction to efficiently capture the interactions of asynchronous decisions, and we theoretically demonstrate its advantages in handling asynchronous tasks. Experimental results show that on two asynchronous decision-making benchmarks, Overcooked and POAC, MVD not only consistently outperforms state-of-the-art MARL methods but also provides the interpretability for asynchronous cooperation.