Computational notebooks became indispensable tools for research-related development, offering unprecedented interactivity and flexibility in the development process. However, these benefits come at the cost of reproducibility and an increased potential for bugs. There are many tools for bug fixing; however, they are generally targeted at the classical linear code. With the rise of code-fluent Large Language Models, a new stream of smart bug-fixing tools has emerged. However, the applicability of those tools is still problematic for non-linear computational notebooks. In this paper, we propose a potential solution for resolving errors in computational notebooks via an iterative LLM-based agent. We discuss the questions raised by this approach and share a novel dataset of computational notebooks containing bugs to facilitate the research of the proposed approach.

The confluence of the advancement of Autonomous Vehicles (AVs) and the maturity of Vehicle-to-Everything (V2X) communication has enabled the capability of cooperative connected and automated vehicles (CAVs). Building on top of cooperative perception, this paper explores the feasibility and effectiveness of cooperative motion prediction. Our method, CMP, takes LiDAR signals as input to enhance tracking and prediction capabilities. Unlike previous work that focuses separately on either cooperative perception or motion prediction, our framework, to the best of our knowledge, is the first to address the unified problem where CAVs share information in both perception and prediction modules. Incorporated into our design is the unique capability to tolerate realistic V2X bandwidth limitations and transmission delays, while dealing with bulky perception representations. We also propose a prediction aggregation module, which unifies the predictions obtained by different CAVs and generates the final prediction. Through extensive experiments and ablation studies, we demonstrate the effectiveness of our method in cooperative perception, tracking, and motion prediction tasks. In particular, CMP reduces the average prediction error by 17.2\% with fewer missing detections compared with the no cooperation setting. Our work marks a significant step forward in the cooperative capabilities of CAVs, showcasing enhanced performance in complex scenarios.

Growing concerns about safety and alignment of AI systems highlight the importance of embedding moral capabilities in artificial agents. A promising solution is the use of learning from experience, i.e., Reinforcement Learning. In multi-agent (social) environments, complex population-level phenomena may emerge from interactions between individual learning agents. Many of the existing studies rely on simulated social dilemma environments to study the interactions of independent learning agents. However, they tend to ignore the moral heterogeneity that is likely to be present in societies of agents in practice. For example, at different points in time a single learning agent may face opponents who are consequentialist (i.e., caring about maximizing some outcome over time) or norm-based (i.e., focusing on conforming to a specific norm here and now). The extent to which agents' co-development may be impacted by such moral heterogeneity in populations is not well understood. In this paper, we present a study of the learning dynamics of morally heterogeneous populations interacting in a social dilemma setting. Using a Prisoner's Dilemma environment with a partner selection mechanism, we investigate the extent to which the prevalence of diverse moral agents in populations affects individual agents' learning behaviors and emergent population-level outcomes. We observe several types of non-trivial interactions between pro-social and anti-social agents, and find that certain classes of moral agents are able to steer selfish agents towards more cooperative behavior.

We consider a discrete-time model of continuous-time distributed optimization over dynamic directed-graphs (digraphs) with applications to distributed learning. Our optimization algorithm works over general strongly connected dynamic networks under switching topologies, e.g., in mobile multi-agent systems and volatile networks due to link failures. Compared to many existing lines of work, there is no need for bi-stochastic weight designs on the links. The existing literature mostly needs the link weights to be stochastic using specific weight-design algorithms needed both at the initialization and at all times when the topology of the network changes. This paper eliminates the need for such algorithms and paves the way for distributed optimization over time-varying digraphs. We derive the bound on the gradient-tracking step-size and discrete time-step for convergence and prove dynamic stability using arguments from consensus algorithms, matrix perturbation theory, and Lyapunov theory. This work, particularly, is an improvement over existing stochastic-weight undirected networks in case of link removal or packet drops. This is because the existing literature may need to rerun time-consuming and computationally complex algorithms for stochastic design, while the proposed strategy works as long as the underlying network is weight-symmetric and balanced. The proposed optimization framework finds applications to distributed classification and learning.

In multi-agent reinforcement learning (MARL), agents repeatedly interact across time and revise their strategies as new data arrives, producing a sequence of strategy profiles. This paper studies sequences of strategies satisfying a pairwise constraint inspired by policy updating in reinforcement learning, where an agent who is best responding in period $t$ does not switch its strategy in the next period $t+1$. This constraint merely requires that optimizing agents do not switch strategies, but does not constrain the other non-optimizing agents in any way, and thus allows for exploration. Sequences with this property are called satisficing paths, and arise naturally in many MARL algorithms. A fundamental question about strategic dynamics is such: for a given game and initial strategy profile, is it always possible to construct a satisficing path that terminates at an equilibrium strategy? The resolution of this question has implications about the capabilities or limitations of a class of MARL algorithms. We answer this question in the affirmative for mixed extensions of finite normal-form games.%

This paper presents two algorithms for multi-agent dynamic coverage in spatiotemporal environments, where the coverage algorithms are informed by the method of data assimilation. In particular, we show that by considering the information assimilation algorithm, here a Numerical Gaussian Process Kalman Filter, the influence of measurements taken at one position on the uncertainty of the estimate at another location can be computed. We use this relationship to propose new coverage algorithms. Furthermore, we show that the controllers naturally extend to the multi-agent context, allowing for a distributed-control central-information paradigm for multi-agent coverage. Finally, we demonstrate the algorithms through a realistic simulation of a team of UAVs collecting wind data over a region in Austria.

Challenge the champ tournaments are one of the simplest forms of competition, where a (initially selected) champ is repeatedly challenged by other players. If a player beats the champ, then that player is considered the new (current) champ. Each player in the competition challenges the current champ once in a fixed order. The champ of the last round is considered the winner of the tournament. We investigate a setting where players can be bribed to lower their winning probability against the initial champ. The goal is to maximize the probability of the initial champ winning the tournament by bribing the other players, while not exceeding a given budget for the bribes. Mattei et al. [Journal of Applied Logic, 2015] showed that the problem can be solved in pseudo-polynomial time, and that it is in XP when parameterized by the number of players. We show that the problem is weakly NP-hard and W[1]-hard when parameterized by the number of players. On the algorithmic side, we show that the problem is fixed-parameter tractable when parameterized either by the number of different bribe values or the number of different probability values. To this end, we establish several results that are of independent interest. In particular, we show that the product knapsack problem is W[1]-hard when parameterized by the number of items in the knapsack, and that constructive bribery for cup tournaments is W[1]-hard when parameterized by the number of players. Furthermore, we present a novel way of designing mixed integer linear programs, ensuring optimal solutions where all variables are integers.

Its inherent ability to tackle challenges surpassing the capacity of individual agents, coupled with its robustness against failures and disturbances, renders it applicable across diverse domains, ranging from robotics to social networks [2, 3]. Among the myriad of tasks within MAS, formation control emerges as a quintessential endeavor, entailing multiple agents orchestrating themselves into various formations while preserving the integrity of the ensemble, a task that has garnered considerable research interest in recent years [4]. Despite the plethora of control algorithms proposed for multi-agent tasks, many of these approaches hinge on the premise of dense interaction dynamics, necessitating rigid interaction topologies among agents to achieve desired outcomes effectively [5, 6]. For instance, the method proposed by De Marina et al. underscores the importance of a rigid interaction topology for successful task execution [5]. In contrast, the cyclic pursuit method stands out for its remarkable ability to achieve formation control with limited information, relying solely on the relative position of the agent ahead, thus offering a more flexible and scalable approach to formation control within MAS [7, 8, 9, 10]. Originating as an attempt to mimic biological entities such as dogs and ants, cyclic pursuit has since evolved into a versatile approach known as the "bugs" problem, which has garnered considerable attention in both academic and industrial circles [7, 8]. Previous studies have extensively explored its dynamics across various agent models, encompassing ants, crickets, frogs, and others, further solidifying its status as a cornerstone of formation control within MAS [10, 11]. Motivated by the question of whether cyclic pursuit enables agents to form shapes beyond those previously demonstrated, this study proposes a novel method for forming desired shapes based on the cyclic pursuit strategy. Addressing two distinct problem settings, we investigate the sufficiency of information for agents to achieve formation for any given shape.

Large-scale heterogeneous multiagent systems feature various realistic factors in the real world, such as agents with diverse abilities and overall system cost. In comparison to homogeneous systems, heterogeneous systems offer significant practical advantages. Nonetheless, they also present challenges for multiagent reinforcement learning, including addressing the non-stationary problem and managing an imbalanced number of agents with different types. We propose a Prioritized Heterogeneous League Reinforcement Learning (PHLRL) method to address large-scale heterogeneous cooperation problems. PHLRL maintains a record of various policies that agents have explored during their training and establishes a heterogeneous league consisting of diverse policies to aid in future policy optimization. Furthermore, we design a prioritized policy gradient approach to compensate for the gap caused by differences in the number of different types of agents. Next, we use Unreal Engine to design a large-scale heterogeneous cooperation benchmark named Large-Scale Multiagent Operation (LSMO), which is a complex two-team competition scenario that requires collaboration from both ground and airborne agents. We use experiments to show that PHLRL outperforms state-of-the-art methods, including QTRAN and QPLEX in LSMO.

The automated generation of diverse and complex training scenarios has been an important ingredient in many complex learning tasks. Especially in real-world application domains, such as autonomous driving, auto-curriculum generation is considered vital for obtaining robust and general policies. However, crafting traffic scenarios with multiple, heterogeneous agents is typically considered as a tedious and time-consuming task, especially in more complex simulation environments. In our work, we introduce MATS-Gym, a Multi-Agent Traffic Scenario framework to train agents in CARLA, a high-fidelity driving simulator. MATS-Gym is a multi-agent training framework for autonomous driving that uses partial scenario specifications to generate traffic scenarios with variable numbers of agents. This paper unifies various existing approaches to traffic scenario description into a single training framework and demonstrates how it can be integrated with techniques from unsupervised environment design to automate the generation of adaptive auto-curricula. The code is available at https://github.com/AutonomousDrivingExaminer/mats-gym.