Recent advancement in reinforcement learning research has witnessed much development on multiagent reinforcement learning (MARL). However, most of the works focus on risk-neutral agents, which may not be suitable for modeling the real world. For example, in investment activities, different investors have different risk preferences depending on their roles in the market. Some act as speculators and are risk-seeking, while others are bound by regulatory constraints and are thus risk-averse. Another example is multi-player online role-playing games, where each of the players can be considered an agent. Whereas some (risk-seeking) players enjoy exploring uncharted regions in the game, others (risk-averse players) prefer to playing in areas that are well explored and come with less uncertainty. It is not hard to see that in the above examples, modeling each agent as uniformly risk-neutral is inappropriate. This naturally calls for a more sophisticated modeling framework that takes into account of heterogeneous risk preferences of agents. In this paper, we study the problem of risk-sensitive MARL under the setting of general-sum Markov games (MGs), a more realistic multi-agent model in which the agents may take different risk preferences.

Trustworthiness is a crucial concept in the context of human-robot interaction. Cooperative robots must be transparent regarding their decision-making process, especially when operating in a human-oriented environment. This paper presents a comprehensive end-to-end framework aimed at fostering trustworthy bidirectional human-robot interaction in collaborative environments for the social navigation of mobile robots. In this framework, the robot communicates verbally while the human guides with gestures. Our method enables a mobile robot to predict the trajectory of people and adjust its route in a socially-aware manner. In case of conflict between human and robot decisions, detected through visual examination, the route is dynamically modified based on human preference while verbal communication is maintained. We present our pipeline, framework design, and preliminary experiments that form the foundation of our proposition.

This work focuses on the entropy-regularized independent natural policy gradient (NPG) algorithm in multi-agent reinforcement learning. In this work, agents are assumed to have access to an oracle with exact policy evaluation and seek to maximize their respective independent rewards. Each individual's reward is assumed to depend on the actions of all the agents in the multi-agent system, leading to a game between agents. We assume all agents make decisions under a policy with bounded rationality, which is enforced by the introduction of entropy regularization. In practice, a smaller regularization implies the agents are more rational and behave closer to Nash policies. On the other hand, agents with larger regularization acts more randomly, which ensures more exploration. We show that, under sufficient entropy regularization, the dynamics of this system converge at a linear rate to the quantal response equilibrium (QRE). Although regularization assumptions prevent the QRE from approximating a Nash equilibrium, our findings apply to a wide range of games, including cooperative, potential, and two-player matrix games. We also provide extensive empirical results on multiple games (including Markov games) as a verification of our theoretical analysis.

Autonomous virtual agents are often limited by their singular mode of interaction with real-world environments, restricting their versatility. To address this, we propose the Multi-Modal Agent Collaboration framework (MMAC-Copilot), a framework utilizes the collective expertise of diverse agents to enhance interaction ability with operating systems. The framework introduces a team collaboration chain, enabling each participating agent to contribute insights based on their specific domain knowledge, effectively reducing the hallucination associated with knowledge domain gaps. To evaluate the performance of MMAC-Copilot, we conducted experiments using both the GAIA benchmark and our newly introduced Visual Interaction Benchmark (VIBench). VIBench focuses on non-API-interactable applications across various domains, including 3D gaming, recreation, and office scenarios. MMAC-Copilot achieved exceptional performance on GAIA, with an average improvement of 6.8\% over existing leading systems. Furthermore, it demonstrated remarkable capability on VIBench, particularly in managing various methods of interaction within systems and applications. These results underscore MMAC-Copilot's potential in advancing the field of autonomous virtual agents through its innovative approach to agent collaboration.

Autonomous exploration of unknown environments using a team of mobile robots demands distributed perception and planning strategies to enable efficient and scalable performance. Ideally, each robot should update its map and plan its motion not only relying on its own observations, but also considering the observations of its peers. Centralized solutions to multi-robot coordination are susceptible to central node failure and require a sophisticated communication infrastructure for reliable operation. Current decentralized active mapping methods consider simplistic robot models with linear-Gaussian observations and Euclidean robot states. In this work, we present a distributed multi-robot mapping and planning method, called Riemannian Optimization for Active Mapping (ROAM). We formulate an optimization problem over a graph with node variables belonging to a Riemannian manifold and a consensus constraint requiring feasible solutions to agree on the node variables. We develop a distributed Riemannian optimization algorithm that relies only on one-hop communication to solve the problem with consensus and optimality guarantees. We show that multi-robot active mapping can be achieved via two applications of our distributed Riemannian optimization over different manifolds: distributed estimation of a 3-D semantic map and distributed planning of SE(3) trajectories that minimize map uncertainty. We demonstrate the performance of ROAM in simulation and real-world experiments using a team of robots with RGB-D cameras.

Applications of large-scale mobile multi-robot systems can be beneficial over monolithic robots because of higher potential for robustness and scalability. Developing controllers for multi-robot systems is challenging because the multitude of interactions is hard to anticipate and difficult to model. Automatic design using machine learning or evolutionary robotics seem to be options to avoid that challenge, but bring the challenge of designing reward or fitness functions. Generic reward and fitness functions seem unlikely to exist and task-specific rewards often have undesired side effects. Approaches of so-called innate motivation try to avoid the specific formulation of rewards and work instead with different drivers, such as curiosity. Our approach to innate motivation is to minimize surprise, which we implement by maximizing the accuracy of the swarm robot's sensor predictions using neuroevolution. A unique advantage of the swarm robot case is that swarm members populate the robot's environment and can trigger more active behaviors in a self-referential loop. We summarize our previous simulation-based results concerning behavioral diversity, robustness, scalability, and engineered self-organization, and put them into context. In several new studies, we analyze the influence of the optimizer's hyperparameters, the scalability of evolved behaviors, and the impact of realistic robot simulations. Finally, we present results using real robots that show how the reality gap can be bridged.

The significance of network structures in promoting group cooperation within social dilemmas has been widely recognized. Prior studies attribute this facilitation to the assortment of strategies driven by spatial interactions. Although reinforcement learning has been employed to investigate the impact of dynamic interaction on the evolution of cooperation, there remains a lack of understanding about how agents develop neighbour selection behaviours and the formation of strategic assortment within an explicit interaction structure. To address this, our study introduces a computational framework based on multi-agent reinforcement learning in the spatial Prisoner's Dilemma game. This framework allows agents to select dilemma strategies and interacting neighbours based on their long-term experiences, differing from existing research that relies on preset social norms or external incentives. By modelling each agent using two distinct Q-networks, we disentangle the coevolutionary dynamics between cooperation and interaction. The results indicate that long-term experience enables agents to develop the ability to identify non-cooperative neighbours and exhibit a preference for interaction with cooperative ones. This emergent self-organizing behaviour leads to the clustering of agents with similar strategies, thereby increasing network reciprocity and enhancing group cooperation.

Nowadays, large-scale foundation models are being increasingly integrated into numerous safety-critical applications, including human-autonomy teaming (HAT) within transportation, medical, and defence domains. Consequently, the inherent 'black-box' nature of these sophisticated deep neural networks heightens the significance of fostering mutual understanding and trust between humans and autonomous systems. To tackle the transparency challenges in HAT, this paper conducts a thoughtful study on the underexplored domain of Explainable Interface (EI) in HAT systems from a human-centric perspective, thereby enriching the existing body of research in Explainable Artificial Intelligence (XAI). We explore the design, development, and evaluation of EI within XAI-enhanced HAT systems. To do so, we first clarify the distinctions between these concepts: EI, explanations and model explainability, aiming to provide researchers and practitioners with a structured understanding. Second, we contribute to a novel framework for EI, addressing the unique challenges in HAT. Last, our summarized evaluation framework for ongoing EI offers a holistic perspective, encompassing model performance, human-centered factors, and group task objectives. Based on extensive surveys across XAI, HAT, psychology, and Human-Computer Interaction (HCI), this review offers multiple novel insights into incorporating XAI into HAT systems and outlines future directions.

We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting reflects many challenges of real-world robotics, including active perception, agile full-body control, and long-horizon planning in a dynamic, partially-observable, multi-agent domain. We rely on large-scale, simulation-based data generation to obtain complex behaviors from egocentric vision which can be successfully transferred to physical robots using low-cost sensors. To achieve adequate visual realism, our simulation combines rigid-body physics with learned, realistic rendering via multiple Neural Radiance Fields (NeRFs). We combine teacher-based multi-agent RL and cross-experiment data reuse to enable the discovery of sophisticated soccer strategies. We analyze active-perception behaviors including object tracking and ball seeking that emerge when simply optimizing perception-agnostic soccer play. The agents display equivalent levels of performance and agility as policies with access to privileged, ground-truth state. To our knowledge, this paper constitutes a first demonstration of end-to-end training for multi-agent robot soccer, mapping raw pixel observations to joint-level actions, that can be deployed in the real world. Videos of the game-play and analyses can be seen on our website https://sites.google.com/view/vision-soccer .

Social agents with finitely nested opponent models are vulnerable to manipulation by agents with deeper reasoning and more sophisticated opponent modelling. This imbalance, rooted in logic and the theory of recursive modelling frameworks, cannot be solved directly. We propose a computational framework, $\aleph$-IPOMDP, augmenting model-based RL agents' Bayesian inference with an anomaly detection algorithm and an out-of-belief policy. Our mechanism allows agents to realize they are being deceived, even if they cannot understand how, and to deter opponents via a credible threat. We test this framework in both a mixed-motive and zero-sum game. Our results show the $\aleph$ mechanism's effectiveness, leading to more equitable outcomes and less exploitation by more sophisticated agents. We discuss implications for AI safety, cybersecurity, cognitive science, and psychiatry.