This study offers a new paradigm of individual-level modeling to address the grand challenge of incorporating human behavior in epidemic models. Using generative artificial intelligence in an agent-based epidemic model, each agent is empowered to make its own reasonings and decisions via connecting to a large language model such as ChatGPT. Through various simulation experiments, we present compelling evidence that generative agents mimic real-world behaviors such as quarantining when sick and self-isolation when cases rise. Collectively, the agents demonstrate patterns akin to multiple waves observed in recent pandemics followed by an endemic period. Moreover, the agents successfully flatten the epidemic curve. This study creates potential to improve dynamic system modeling by offering a way to represent human brain, reasoning, and decision making. One-Sentence Summary: A new modeling technique using generative AI applied to an epidemic to incorporate human reasoning and decision making.

This paper presents an overview of robot failure detection work from HRI and adjacent fields using failures as an opportunity to examine robot explanation behaviours. As humanoid robots remain experimental tools in the early 2020s, interactions with robots are situated overwhelmingly in controlled environments, typically studying various interactional phenomena. Such interactions suffer from real-world and large-scale experimentation and tend to ignore the 'imperfectness' of the everyday user. Robot explanations can be used to approach and mitigate failures, by expressing robot legibility and incapability, and within the perspective of common-ground. In this paper, I discuss how failures present opportunities for explanations in interactive conversational robots and what the potentials are for the intersection of HRI and explainability research.

Deep learning has achieved great success in recent years, mainly due to advances in machine learning algorithms and computer hardware. As a result, it has become an indispensable tool in a wide range of fields, both in research and in practical applications. Specifically, in finance, deep learning has been applied extensively to predict stock prices movements using limit order book data. This technique is particularly effective in handling complex data which statistical models often struggle to manage. Notable works in the recent literature include [34, 26, 25, 33]. In particular, contrastive learning (CL) is a powerful technique in deep learning that has led to significant advances in representation learning.

Double Auction enables decentralized transfer of goods between multiple buyers and sellers, thus underpinning functioning of many online marketplaces. Buyers and sellers compete in these markets through bidding, but do not often know their own valuation a-priori. As the allocation and pricing happens through bids, the profitability of participants, hence sustainability of such markets, depends crucially on learning respective valuations through repeated interactions. We initiate the study of Double Auction markets under bandit feedback on both buyers' and sellers' side. We show with confidence bound based bidding, and `Average Pricing' there is an efficient price discovery among the participants. In particular, the regret on combined valuation of the buyers and the sellers -- a.k.a. the social regret -- is $O(\log(T)/\Delta)$ in $T$ rounds, where $\Delta$ is the minimum price gap. Moreover, the buyers and sellers exchanging goods attain $O(\sqrt{T})$ regret, individually. The buyers and sellers who do not benefit from exchange in turn only experience $O(\log{T}/ \Delta)$ regret individually in $T$ rounds. We augment our upper bound by showing that $\omega(\sqrt{T})$ individual regret, and $\omega(\log{T})$ social regret is unattainable in certain Double Auction markets. Our paper is the first to provide decentralized learning algorithms in a two-sided market where \emph{both sides have uncertain preference} that need to be learned.

Learning multi-agent system dynamics has been extensively studied for various real-world applications, such as molecular dynamics in biology. Most of the existing models are built to learn single system dynamics from observed historical data and predict the future trajectory. In practice, however, we might observe multiple systems that are generated across different environments, which differ in latent exogenous factors such as temperature and gravity. One simple solution is to learn multiple environment-specific models, but it fails to exploit the potential commonalities among the dynamics across environments and offers poor prediction results where per-environment data is sparse or limited. Here, we present GG-ODE (Generalized Graph Ordinary Differential Equations), a machine learning framework for learning continuous multi-agent system dynamics across environments. Our model learns system dynamics using neural ordinary differential equations (ODE) parameterized by Graph Neural Networks (GNNs) to capture the continuous interaction among agents. We achieve the model generalization by assuming the dynamics across different environments are governed by common physics laws that can be captured via learning a shared ODE function. The distinct latent exogenous factors learned for each environment are incorporated into the ODE function to account for their differences. To improve model performance, we additionally design two regularization losses to (1) enforce the orthogonality between the learned initial states and exogenous factors via mutual information minimization; and (2) reduce the temporal variance of learned exogenous factors within the same system via contrastive learning. Experiments over various physical simulations show that our model can accurately predict system dynamics, especially in the long range, and can generalize well to new systems with few observations.

Autonomous vehicles are expected to travel in urban environments in the future for increased safety and overall efficiency. They could be of different car brands running different navigation & communication systems that do not share their route-choosing processes or travel data, either due to lack of communication or due to privacy restrictions. To avoid traffic congestion, such as those caused by non-cooperating human drivers nowadays, independent autonomous vehicles need to have a method for distributing traffic in the environment without communication. Motivated by this real-world scenario, in this paper we consider the problem of path planning for a large number of privacy-aware robots in a complex, cluttered indoor or urban environment with uncertainties (other unpredictable agents such as pedestrians), where the robots need to be well-distributed throughout the environment and avoid congestion in any region, but are not allowed to communicate or share their location data or intents with other robots. This is relevant to avoiding congestion in distributed vehicle routing problems when a vehicle's location/intent cannot be shared either due to lack of communication or due to privacy restrictions.

In this paper, we study the problem where a group of agents aim to collaboratively learn a common static latent function through streaming data. We propose a lightweight distributed Gaussian process regression (GPR) algorithm that is cognizant of agents' limited capabilities in communication, computation and memory. Each agent independently runs agent-based GPR using local streaming data to predict test points of interest; then the agents collaboratively execute distributed GPR to obtain global predictions over a common sparse set of test points; finally, each agent fuses results from distributed GPR with agent-based GPR to refine its predictions. By quantifying the transient and steady-state performances in predictive variance and error, we show that limited inter-agent communication improves learning performances in the sense of Pareto. Monte Carlo simulation is conducted to evaluate the developed algorithm.

We propose MAP-NBV, a prediction-guided active algorithm for 3D reconstruction with multi-agent systems. Prediction-based approaches have shown great improvement in active perception tasks by learning the cues about structures in the environment from data. But these methods primarily focus on single-agent systems. We design a next-best-view approach that utilizes geometric measures over the predictions and jointly optimizes the information gain and control effort for efficient collaborative 3D reconstruction of the object. Our method achieves 22.75% improvement over the prediction-based single-agent approach and 15.63% improvement over the non-predictive multi-agent approach. We make our code publicly available through our project website: http://raaslab.org/projects/MAPNBV/

Large-scale systems where agents interact competitively with each other have received significant attention recently, motivated by applications in power systems (Shi et al., 2022), EV charging (Lee et al., 2022), and board games (Silver et al., 2017), etc. Controlling such systems can be challenging due to the scale of the system, uncertainty about the model, communication constraints, and the interaction between agents. Inspired by the recent success of reinforcement learning (RL), there is an increasing interest in applying RL methods to environments with multi-agent interactions. However, in multi-agent RL (MARL), the analysis of the system behavior becomes challenging due to the time-varying nature of the environment faced by each agent, which results from the (time-varying) competitive decisions of other agents. As a result, the theoretical analysis of MARL, especially in the competitive setting, is still limited, especially when it comes to large-scale systems. The results of MARL in competitive settings to this point have tended to focus on games with a small number of players, e.g., 2-player zero-sum stochastic games (Littman, 1994), or games with special structure, e.g., Markov potential games (MPGs) (Fox et al., 2022). MPGs in particular provide a setting in which the challenges of large-scale systems can be studied.

This work presents a 3D multi-robot exploration framework for a team of UGVs moving on uneven terrains. The framework was designed by casting the two-level coordination strategy presented in [1] into the context of multi-robot exploration. The resulting distributed exploration technique minimizes and explicitly manages the occurrence of conflicts and interferences in the robot team. Each robot selects where to scan next by using a receding horizon next-best-view approach [2]. A sampling-based tree is directly expanded on segmented traversable regions of the terrain 3D map to generate the candidate next viewpoints. During the exploration, users can assign locations with higher priorities on-demand to steer the robot exploration toward areas of interest. The proposed framework can be also used to perform coverage tasks in the case a map of the environment is a priori provided as input. An open-source implementation is available online.