Classical reactive synthesis approaches aim to synthesize a reactive system that always satisfies a given specifications. These approaches often reduce to playing a two-player zero-sum game where the goal is to synthesize a winning strategy. However, in many pragmatic domains, such as robotics, a winning strategy does not always exist, yet it is desirable for the system to make an effort to satisfy its requirements instead of "giving up". To this end, this paper investigates the notion of admissible strategies, which formalize "doing-your-best", in quantitative reachability games. We show that, unlike the qualitative case, quantitative admissible strategies are history-dependent even for finite payoff functions, making synthesis a challenging task. In addition, we prove that admissible strategies always exist but may produce undesirable optimistic behaviors. To mitigate this, we propose admissible winning strategies, which enforce the best possible outcome while being admissible. We show that both strategies always exist but are not memoryless. We provide necessary and sufficient conditions for the existence of both strategies and propose synthesis algorithms. Finally, we illustrate the strategies on gridworld and robot manipulator domains.

Current approaches to automated code generation often rely on monolithic models that lack real-time adaptability and scalability. This limitation is particularly evident in complex programming tasks that require dynamic adjustment and efficiency. The integration of neuroscience principles into Natural Language Processing (NLP) has the potential to revolutionize automated code generation. This paper presents CortexCompile, a novel modular system inspired by the specialized functions of the human brain's cortical regions. By emulating the distinct roles of the Prefrontal Cortex, Parietal Cortex, Temporal Lobe, and Motor Cortex, CortexCompile achieves significant advancements in scalability, efficiency, and adaptability compared to traditional monolithic models like GPT-4o. The system's architecture features a Task Orchestration Agent that manages dynamic task delegation and parallel processing, facilitating the generation of highly accurate and optimized code across increasingly complex programming tasks. Experimental evaluations demonstrate that CortexCompile consistently outperforms GPT-4o in development time, accuracy, and user satisfaction, particularly in tasks involving real-time strategy games and first-person shooters. These findings underscore the viability of neuroscience-inspired architectures in addressing the limitations of current NLP models, paving the way for more efficient and human-like AI systems.

In this work we consider a new interpretation of fairness in decision making problems. Building upon existing fairness formulations, we focus on how to reason over fairness from a temporal perspective, taking into account the fairness of a history of past decisions. After introducing the concept of temporal fairness, we propose three approaches that incorporate temporal fairness in decision making problems formulated as optimization problems. We present a qualitative evaluation of our approach in four different domains and compare the solutions against a baseline approach that does not consider the temporal aspect of fairness.

Computational models of human learning can play a significant role in enhancing our knowledge about nuances in theoretical and qualitative learning theories and frameworks. There are many existing frameworks in educational settings that have shown to be verified using empirical studies, but at times we find these theories make conflicting claims or recommendations for instruction. In this study, we propose a new computational model of human learning, Procedural ABICAP, that reconciles the ICAP, Knowledge-Learning-Instruction (KLI), and cognitive load theory (CLT) frameworks for learning procedural knowledge. ICAP assumes that constructive learning generally yields better learning outcomes, while theories such as KLI and CLT claim that this is not always true. We suppose that one reason for this may be that ICAP is primarily used for conceptual learning and is underspecified as a framework for thinking about procedural learning. We show how our computational model, both by design and through simulations, can be used to reconcile different results in the literature. More generally, we position our computational model as an executable theory of learning that can be used to simulate various educational settings.

Self-awareness is a critical factor in social human-human interaction and, hence, in social HCI interaction. Increasing self-awareness through mirrors or video recordings is common in face-to-face trainings, since it influences antecedents of self-awareness like explicit identification and implicit affective identification (affinity). However, increasing self-awareness has been scarcely examined in virtual trainings with virtual avatars, which allow for adjusting the similarity, e.g. to avoid negative effects of self-consciousness. Automatic visual similarity in avatars is an open issue related to high costs. It is important to understand which features need to be manipulated and which degree of similarity is necessary for self-awareness to leverage the added value of using avatars for self-awareness. This article examines the relationship between avatar visual similarity and increasing self-awareness in virtual training environments. We define visual similarity based on perceptually important facial features for human-human identification and develop a theory-based methodology to systematically manipulate visual similarity of virtual avatars and support self-awareness. Three personalized versions of virtual avatars with varying degrees of visual similarity to participants were created (weak, medium and strong facial features manipulation). In a within-subject study (N=33), we tested effects of degree of similarity on perceived similarity, explicit identification and implicit affective identification (affinity). Results show significant differences between the weak similarity manipulation, and both the strong manipulation and the random avatar for all three antecedents of self-awareness. An increasing degree of avatar visual similarity influences antecedents of self-awareness in virtual environments.

Offline multi-agent reinforcement learning (MARL) is increasingly recognized as crucial for effectively deploying RL algorithms in environments where real-time interaction is impractical, risky, or costly. In the offline setting, learning from a static dataset of past interactions allows for the development of robust and safe policies without the need for live data collection, which can be fraught with challenges. Building on this foundational importance, we present EAQ, Episodes Augmentation guided by Q-total loss, a novel approach for offline MARL framework utilizing diffusion models. EAQ integrates the Q-total function directly into the diffusion model as a guidance to maximize the global returns in an episode, eliminating the need for separate training. Our focus primarily lies on cooperative scenarios, where agents are required to act collectively towards achieving a shared goal-essentially, maximizing global returns. Consequently, we demonstrate that our episodes augmentation in a collaborative manner significantly boosts offline MARL algorithm compared to the original dataset, improving the normalized return by +17.3% and +12.9% for medium and poor behavioral policies in SMAC simulator, respectively.

Centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to epsilon-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. This paper presents a novel and more scalable alternative, namely sequential-move centralized training for decentralized execution. This paradigm further pushes the applicability of Bellman's principle of optimality, raising three new properties. First, it allows a central planner to reason upon sufficient sequential-move statistics instead of prior simultaneous-move ones. Next, it proves that epsilon-optimal value functions are piecewise linear and convex in sufficient sequential-move statistics. Finally, it drops the complexity of the backup operators from double exponential to polynomial at the expense of longer planning horizons. Besides, it makes it easy to use single-agent methods, e.g., SARSA algorithm enhanced with these findings applies while still preserving convergence guarantees. Experiments on two- as well as many-agent domains from the literature against epsilon-optimal simultaneous-move solvers confirm the superiority of the novel approach. This paradigm opens the door for efficient planning and reinforcement learning methods for multi-agent systems.

In this dissertation, we investigate the issue of robust localization in swarms of heterogeneous mobile agents with multiple and time-varying sensing modalities. Our focus is the development of filter-based and decoupled estimators under the assumption that agents possess communication and processing capabilities. Based on the findings from Distributed Collaborative State Estimation and modular sensor fusion, we propose a novel Kalman filter decoupling paradigm, which is termed Isolated Kalman Filtering (IKF). This paradigm is formally discussed and the treatment of delayed measurement is studied. The impact of approximation made was investigated on different observation graphs and the filter credibility was evaluated on a linear system in a Monte Carlo simulation. Finally, we propose a multi-agent modular sensor fusion approach based on the IKF paradigm, in order to cooperatively estimate the global state of a multi-agent system in a distributed way and fuse information provided by different on-board sensors in a computationally efficient way. As a consequence, this approach can be performed distributed among agents, while (i) communication between agents is only required at the moment of inter-agent joint observations, (ii) one agent acts as interim master to process state corrections isolated, (iii) agents can be added and removed from the swarm, (iv) each agent's full state can vary during mission (each local sensor suite can be truly modular), and (v) delayed and multi-rate sensor updates are supported. Extensive evaluation on realistic simulated and real-world data sets show that the proposed Isolated Kalman Filtering (IKF) paradigm, is applicable for both, truly modular single agent estimation and distributed collaborative multi-agent estimation problems.

With more autonomous vehicles (AVs) sharing roadways with human-driven vehicles (HVs), ensuring safe and courteous maneuvers that respect HVs' behavior becomes increasingly important. To promote both safety and courtesy in AV's behavior, an extension of Control Barrier Functions (CBFs)-inspired risk evaluation framework is proposed in this paper by considering both noisy observed positions and velocities of surrounding vehicles. The perceived risk by the ego vehicle can be visualized as a risk map that reflects the understanding of the surrounding environment and thus shows the potential for facilitating safe and courteous driving. By incorporating the risk evaluation framework into the Model Predictive Control (MPC) scheme, we propose a Courteous MPC for ego AV to generate courteous behaviors that 1) reduce the overall risk imposed on other vehicles and 2) respect the hard safety constraints and the original objective for efficiency. We demonstrate the performance of the proposed Courteous MPC via theoretical analysis and simulation experiments.

Large language models (LLMs) have had a significant impact on diverse research domains, including medicine and healthcare. However, the potential of LLMs as copilots in medical education remains underexplored. Current AI-assisted educational tools are limited by their solitary learning approach and inability to simulate the multi-disciplinary and interactive nature of actual medical training. To address these limitations, we propose MEDCO (Medical EDucation COpilots), a novel multi-agent-based copilot system specially developed to emulate real-world medical training environments. MEDCO incorporates three primary agents: an agentic patient, an expert doctor, and a radiologist, facilitating a multi-modal and interactive learning environment. Our framework emphasizes the learning of proficient question-asking skills, multi-disciplinary collaboration, and peer discussions between students. Our experiments show that simulated virtual students who underwent training with MEDCO not only achieved substantial performance enhancements comparable to those of advanced models, but also demonstrated human-like learning behaviors and improvements, coupled with an increase in the number of learning samples. This work contributes to medical education by introducing a copilot that implements an interactive and collaborative learning approach. It also provides valuable insights into the effectiveness of AI-integrated training paradigms.