The tasks of object detection and trajectory forecasting play a crucial role in understanding the scene for autonomous driving. These tasks are typically executed in a cascading manner, making them prone to compounding errors. Furthermore, there is usually a very thin interface between the two tasks, creating a lossy information bottleneck. To address these challenges, our approach formulates the union of the two tasks as a trajectory refinement problem, where the first pose is the detection (current time), and the subsequent poses are the waypoints of the multiple forecasts (future time). To tackle this unified task, we design a refinement transformer that infers the presence, pose, and multi-modal future behaviors of objects directly from LiDAR point clouds and high-definition maps. We call this model DeTra, short for object Detection and Trajectory forecasting. In our experiments, we observe that \ourmodel{} outperforms the state-of-the-art on Argoverse 2 Sensor and Waymo Open Dataset by a large margin, across a broad range of metrics. Last but not least, we perform extensive ablation studies that show the value of refinement for this task, that every proposed component contributes positively to its performance, and that key design choices were made.

The Lucas critique emphasizes the importance of considering the impact of policy changes on the expectations of micro-level agents in macroeconomic policymaking. However, the inherently self-interested nature of large-scale micro-agents, who pursue long-term benefits, complicates the formulation of optimal macroeconomic policies. This paper proposes a novel general framework named Dynamic Stackelberg Mean Field Games (Dynamic SMFG) to model such policymaking within sequential decision-making processes, with the government as the leader and households as dynamic followers. Dynamic SMFGs capture the dynamic interactions among large-scale households and their response to macroeconomic policy changes. To solve dynamic SMFGs, we propose the Stackelberg Mean Field Reinforcement Learning (SMFRL) algorithm, which leverages the population distribution of followers to represent high-dimensional joint state and action spaces. In experiments, our method surpasses macroeconomic policies in the real world, existing AI-based and economic methods. It allows the leader to approach the social optimum with the highest performance, while large-scale followers converge toward their best response to the leader's policy. Besides, we demonstrate that our approach retains effectiveness even when some households do not adopt the SMFG policy. In summary, this paper contributes to the field of AI for economics by offering an effective tool for modeling and solving macroeconomic policy-making issues.

In this paper, we investigate the module-checking problem of pushdown multi-agent systems (PMS) against ATL and ATL* specifications. We establish that for ATL, module checking of PMS is 2EXPTIME-complete, which is the same complexity as pushdown module-checking for CTL. On the other hand, we show that ATL* module-checking of PMS turns out to be 4EXPTIME-complete, hence exponentially harder than both CTL* pushdown module-checking and ATL* model-checking of PMS. Our result for ATL* provides a rare example of a natural decision problem that is elementary yet but with a complexity that is higher than triply exponential-time.

Offline multi-agent reinforcement learning (MARL) is an emerging field with great promise for real-world applications. Unfortunately, the current state of research in offline MARL is plagued by inconsistencies in baselines and evaluation protocols, which ultimately makes it difficult to accurately assess progress, trust newly proposed innovations, and allow researchers to easily build upon prior work. In this paper, we firstly identify significant shortcomings in existing methodologies for measuring the performance of novel algorithms through a representative study of published offline MARL work. Secondly, by directly comparing to this prior work, we demonstrate that simple, well-implemented baselines can achieve state-of-the-art (SOTA) results across a wide range of tasks. Specifically, we show that on 35 out of 47 datasets used in prior work (almost 75% of cases), we match or surpass the performance of the current purported SOTA. Strikingly, our baselines often substantially outperform these more sophisticated algorithms. Finally, we correct for the shortcomings highlighted from this prior work by introducing a straightforward standardised methodology for evaluation and by providing our baseline implementations with statistically robust results across several scenarios, useful for comparisons in future work. Our proposal includes simple and sensible steps that are easy to adopt, which in combination with solid baselines and comparative results, could substantially improve the overall rigour of empirical science in offline MARL moving forward.

The latest breakthroughs in Large Language Models (LLMs), eg., ChatDev, have catalyzed profound transformations, particularly through multi-agent collaboration for software development. LLM agents can collaborate in teams like humans, and follow the waterfall model to sequentially work on requirements analysis, development, review, testing, and other phases to perform autonomous software generation. However, for an agent team, each phase in a single development process yields only one possible outcome. This results in the completion of only one development chain, thereby losing the opportunity to explore multiple potential decision paths within the solution space. Consequently, this may lead to obtaining suboptimal results. To address this challenge, we introduce Cross-Team Collaboration (CTC), a scalable multi-team framework that enables orchestrated teams to jointly propose various decisions and communicate with their insights in a cross-team collaboration environment for superior content generation. Experimental results in software development reveal a notable increase in quality compared to state-of-the-art baselines, underscoring the efficacy of our framework. The significant improvements in story generation demonstrate the promising generalization ability of our framework across various domains. We anticipate that our work will guide LLM agents towards a cross-team paradigm and contribute to their significant growth in but not limited to software development. The code and data will be available at https://github.com/OpenBMB/ChatDev.

A carbon market is a market-based tool that incentivizes economic agents to align individual profits with the global utility, i.e., reducing carbon emissions to tackle climate change. Cap and trade stands as a critical principle based on allocating and trading carbon allowances (carbon emission credit), enabling economic agents to follow planned emissions and penalizing excess emissions. A central authority is responsible for introducing and allocating those allowances in cap and trade. However, the complexity of carbon market dynamics makes accurate simulation intractable, which in turn hinders the design of effective allocation strategies. To address this, we propose an adaptive mechanism design framework, simulating the market using hierarchical, model-free multi-agent reinforcement learning (MARL). Government agents allocate carbon credits, while enterprises engage in economic activities and carbon trading. This framework illustrates agents' behavior comprehensively. Numerical results show MARL enables government agents to balance productivity, equality, and carbon emissions. Our project is available at https://github.com/xwanghan/Carbon-Simulator.

This paper proposes arbitrary-order distributed finite-time differentiator (AODFD) for leader-follower multi-agent systems (MAS) under directed graph by only using relative or absolute output information. By using arbitrary-order distributed finite-time differentiator via relative output information (AODFD-R), each follower agent can obtain the relative output information between itself and leader and the relative output's arbitrary-order derivatives, where the information to be measured is only the local relative output information between each follower agent and its neighboring agents. As a simple extension of AODFD-R, the arbitrary-order distributed finite-time differentiator via absolute output information (AODFD-A) is also given. The finite-time stability of the closed-loop system under AODFD is proved by constructing a Lyapunov function skillfully. Finally, several simulation examples are given to verify the effectiveness of the AODFD.

This paper presents a novel approach to address the Production Routing Problem with Privacy Preserving (PRPPP) in supply chain optimization. The integrated optimization of production, inventory, distribution, and routing decisions in real-world industry applications poses several challenges, including increased complexity, discrepancies between planning and execution, and constraints on information sharing. To mitigate these challenges, this paper proposes the use of intelligent agent negotiation within a hybrid Multi-Agent System (MAS) integrated with optimization algorithms. The MAS facilitates communication and coordination among entities, encapsulates private information, and enables negotiation. This, along with optimization algorithms, makes it a compelling framework for establishing optimal solutions. The approach is supported by real-world applications and synergies between MAS and optimization methods, demonstrating its effectiveness in addressing complex supply chain optimization problems.

Ever since the concepts of dynamic programming were introduced, one of the most difficult challenges has been to adequately address high-dimensional control problems. With growing dimensionality, the utilisation of Deep Neural Networks promises to circumvent the issue of an otherwise exponentially increasing complexity. The paper specifically investigates the sampling issues the Deep Galerkin Method is subjected to. It proposes a drift relaxation-based sampling approach to alleviate the symptoms of high-variance policy approximations. This is validated on mean-field control problems; namely, the variations of the opinion dynamics presented by the Sznajd and the Hegselmann-Krause model. The resulting policies induce a significant cost reduction over manually optimised control functions and show improvements on the Linear-Quadratic Regulator problem over the Deep FBSDE approach.

Previous explanations for the persistence of polarization of opinions have typically included modelling assumptions that predispose the possibility of polarization (e.g.\ repulsive interactions). An exception is recent research showing that polarization is stable when agents form their opinions using reinforcement learning. We show that the polarization observed in this model is not stable, but exhibits consensus asymptotically with probability one. By constructing a link between the reinforcement learning model and the voter model, we argue that the observed polarization is metastable. Finally, we show that a slight modification in the learning process of the agents changes the model from being non-ergodic to being ergodic. Our results show that reinforcement learning may be a powerful method for modelling polarization in opinion dynamics, but that the tools appropriate for analysing such models crucially depend on the properties of the resulting systems. Properties which are determined by the details of the learning process.