In multi-agent reinforcement learning, the behaviors that agents learn in a single Markov Game (MG) are typically confined to the given agent number. Every single MG induced by varying the population may possess distinct optimal joint strategies and game-specific knowledge, which are modeled independently in modern multi-agent reinforcement learning algorithms. In this work, our focus is on creating agents that can generalize across population-varying MGs. Instead of learning a unimodal policy, each agent learns a policy set comprising effective strategies across a variety of games. To achieve this, we propose Meta Representations for Agents (MRA) that explicitly models the game-common and game-specific strategic knowledge. By representing the policy sets with multi-modal latent policies, the game-common strategic knowledge and diverse strategic modes are discovered through an iterative optimization procedure. We prove that by approximately maximizing the resulting constrained mutual information objective, the policies can reach Nash Equilibrium in every evaluation MG when the latent space is sufficiently large. When deploying MRA in practical settings with limited latent space sizes, fast adaptation can be achieved by leveraging the first-order gradient information. Extensive experiments demonstrate the effectiveness of MRA in improving training performance and generalization ability in challenging evaluation games.

We present MotionDiffuser, a diffusion based representation for the joint distribution of future trajectories over multiple agents. Such representation has several key advantages: first, our model learns a highly multimodal distribution that captures diverse future outcomes. Second, the simple predictor design requires only a single L2 loss training objective, and does not depend on trajectory anchors. Third, our model is capable of learning the joint distribution for the motion of multiple agents in a permutation-invariant manner. Furthermore, we utilize a compressed trajectory representation via PCA, which improves model performance and allows for efficient computation of the exact sample log probability. Subsequently, we propose a general constrained sampling framework that enables controlled trajectory sampling based on differentiable cost functions. This strategy enables a host of applications such as enforcing rules and physical priors, or creating tailored simulation scenarios. MotionDiffuser can be combined with existing backbone architectures to achieve top motion forecasting results. We obtain state-of-the-art results for multi-agent motion prediction on the Waymo Open Motion Dataset.

This paper investigates how deep multi-agent reinforcement learning can enable the scalable and privacy-preserving coordination of residential energy flexibility. The coordination of distributed resources such as electric vehicles and heating will be critical to the successful integration of large shares of renewable energy in our electricity grid and, thus, to help mitigate climate change. The pre-learning of individual reinforcement learning policies can enable distributed control with no sharing of personal data required during execution. However, previous approaches for multi-agent reinforcement learning-based distributed energy resources coordination impose an ever greater training computational burden as the size of the system increases. We therefore adopt a deep multi-agent actor-critic method which uses a \emph{centralised but factored critic} to rehearse coordination ahead of execution. Results show that coordination is achieved at scale, with minimal information and communication infrastructure requirements, no interference with daily activities, and privacy protection. Significant savings are obtained for energy users, the distribution network and greenhouse gas emissions. Moreover, training times are nearly 40 times shorter than with a previous state-of-the-art reinforcement learning approach without the factored critic for 30 homes.

Order-driven market simulation mimics the trader behaviors to generate order streams to support interactive studies of financial strategies. In market simulator, the multi-agent approach is commonly adopted due to its explainability. Existing multi-agent systems employ heuristic search to generate order streams, which is inefficient for large-scale simulation. Furthermore, the search-based behavior calibration often leads to inconsistent trader actions under the same general market condition, making the simulation results unstable and difficult to interpret. We propose CaliSim, the first search-free calibration approach multi-agent market simulator which achieves large-scale efficiency and behavior consistency. CaliSim uses meta-learning and devises a surrogate trading system with a consistency loss function for the reproducibility of order stream and trader behaviors. Extensive experiments in the market replay and case studies show that CaliSim achieves state-of-the-art in terms of order stream reproduction with consistent trader behavior and can capture patterns of real markets.

Being able to reason about how one's behaviour can affect the behaviour of others is a core skill required of intelligent driving agents. Despite this, the state of the art struggles to meet the need of agents to discover causal links between themselves and others. Observational approaches struggle because of the non-stationarity of causal links in dynamic environments, and the sparsity of causal interactions while requiring the approaches to work in an online fashion. Meanwhile interventional approaches are impractical as a vehicle cannot experiment with its actions on a public road. To counter the issue of non-stationarity we reformulate the problem in terms of extracted events, while the previously mentioned restriction upon interventions can be overcome with the use of counterfactual simulation. We present three variants of the proposed counterfactual causal discovery method and evaluate these against state of the art observational temporal causal discovery methods across 3396 causal scenes extracted from a real world driving dataset. We find that the proposed method significantly outperforms the state of the art on the proposed task quantitatively and can offer additional insights by comparing the outcome of an alternate series of decisions in a way that observational and interventional approaches cannot.

In this paper, we present a novel framework for enhancing the capabilities of large language models (LLMs) by leveraging the power of multi-agent systems. Our framework introduces a collaborative environment where multiple intelligent agent components, each with distinctive attributes and roles, work together to handle complex tasks more efficiently and effectively. We demonstrate the practicality and versatility of our framework through case studies in artificial general intelligence (AGI), specifically focusing on the Auto-GPT and BabyAGI models. We also examine the "Gorilla" model, which integrates external APIs into the LLM. Our framework addresses limitations and challenges such as looping issues, security risks, scalability, system evaluation, and ethical considerations. By modeling various domains such as courtroom simulations and software development scenarios, we showcase the potential applications and benefits of our proposed multi-agent system. Our framework provides an avenue for advancing the capabilities and performance of LLMs through collaboration and knowledge exchange among intelligent agents.

This paper describes the first open dataset for full-scale and high-speed autonomous racing. Multi-modal sensor data has been collected from fully autonomous Indy race cars operating at speeds of up to 170 mph (273 kph). Six teams who raced in the Indy Autonomous Challenge have contributed to this dataset. The dataset spans 11 interesting racing scenarios across two race tracks which include solo laps, multi-agent laps, overtaking situations, high-accelerations, banked tracks, obstacle avoidance, pit entry and exit at different speeds. The dataset contains data from 27 racing sessions across the 11 scenarios with over 6.5 hours of sensor data recorded from the track. The data is organized and released in both ROS2 and nuScenes format. We have also developed the ROS2-to-nuScenes conversion library to achieve this. The RACECAR data is unique because of the high-speed environment of autonomous racing. We present several benchmark problems on localization, object detection and tracking (LiDAR, Radar, and Camera), and mapping using the RACECAR data to explore issues that arise at the limits of operation of the vehicle.

In game theory, mechanism design is concerned with the design of incentives so that a desired outcome of the game can be achieved. In this paper, we explore the concept of equilibrium design, where incentives are designed to obtain a desirable equilibrium that satisfies a specific temporal logic property. Our study is based on a framework where system specifications are represented as temporal logic formulae, games as quantitative concurrent game structures, and players' goals as mean-payoff objectives. We consider system specifications given by LTL and GR(1) formulae, and show that designing incentives to ensure that a given temporal logic property is satisfied on some/every Nash equilibrium of the game can be achieved in PSPACE for LTL properties and in NP/{\Sigma}P 2 for GR(1) specifications. We also examine the complexity of related decision and optimisation problems, such as optimality and uniqueness of solutions, as well as considering social welfare, and show that the complexities of these problems lie within the polynomial hierarchy. Equilibrium design can be used as an alternative solution to rational synthesis and verification problems for concurrent games with mean-payoff objectives when no solution exists or as a technique to repair concurrent games with undesirable Nash equilibria in an optimal way.

Reasoning about knowledge among multiple agents plays an important role in studying real-world problems in a distributed setting, e.g., in communicating processes, protocols, strategies and games. Multi-agent epistemic logic (EL) [1] and its dynamic extensions, popularly known as dynamic epistemic logics (DEL) [2] are well-known logical systems to specify and reason about such dynamic interactions of knowledge. Traditionally, agents' knowledge is about facts and EL/DEL mostly deals with this phenomenon of'knowing that'. More recently, the notions of'knowing whether', 'knowing why' and'knowing how' have also been investigated from a formal viewpoint [3]. These agents also have expectations about the world around them, and they reason based on what they observe around them, and such observations may or may not match the expectations they have about their surroundings.

We introduce networked communication to the mean-field game framework. In particular, we look at oracle-free settings where $N$ decentralised agents learn along a single, non-episodic evolution path of the empirical system, such as we may encounter for a large range of many-agent cooperation problems in the real-world. We provide theoretical evidence that by spreading improved policies through the network in a decentralised fashion, our sample guarantees are upper-bounded by those of the purely independent-learning case. Moreover, we show empirically that our networked method can give faster convergence in practice, while removing the reliance on a centralised controller. We also demonstrate that our decentralised communication architecture brings significant benefits over both the centralised and independent alternatives in terms of robustness and flexibility to unexpected learning failures and changes in population size. For comparison purposes with our new architecture, we modify recent algorithms for the centralised and independent cases to make their practical convergence feasible: while contributing the first empirical demonstrations of these algorithms in our setting of $N$ agents learning along a single system evolution with only local state observability, we additionally display the empirical benefits of our new, networked approach.