Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their problem-solving capabilities. To address this, we propose a dual self-awareness value decomposition framework, inspired by the notion of dual self-awareness in psychology, that entirely rejects the IGM premise. Each agent consists of an ego policy for action selection and an alter ego value function to solve the credit assignment problem. The value function factorization can ignore the IGM assumption by utilizing an explicit search procedure. On the basis of the above, we also suggest a novel anti-ego exploration mechanism to avoid the algorithm becoming stuck in a local optimum. As the first fully IGM-free value decomposition method, our proposed framework achieves desirable performance in various cooperative tasks.

We propose a method that allows to develop shared understanding between two agents for the purpose of performing a task that requires cooperation. Our method focuses on efficiently establishing successful task-oriented communication in an open multi-agent system, where the agents do not know anything about each other and can only communicate via grounded interaction. The method aims to assist researchers that work on human-machine interaction or scenarios that require a human-in-the-loop, by defining interaction restrictions and efficiency metrics. To that end, we point out the challenges and limitations of such a (diverse) setup, while also restrictions and requirements which aim to ensure that high task performance truthfully reflects the extent to which the agents correctly understand each other. Furthermore, we demonstrate a use-case where our method can be applied for the task of cooperative query answering. We design the experiments by modifying an established ontology alignment benchmark. In this example, the agents want to query each other, while representing different databases, defined in their own ontologies that contain different and incomplete knowledge. Grounded interaction here has the form of examples that consists of common instances, for which the agents are expected to have similar knowledge. Our experiments demonstrate successful communication establishment under the required restrictions, and compare different agent policies that aim to solve the task in an efficient manner.

Diffusion models have experienced a surge of interest as highly expressive yet efficiently trainable probabilistic models. We show that these models are an excellent fit for synthesising human motion that co-occurs with audio, e.g., dancing and co-speech gesticulation, since motion is complex and highly ambiguous given audio, calling for a probabilistic description. Specifically, we adapt the DiffWave architecture to model 3D pose sequences, putting Conformers in place of dilated convolutions for improved modelling power. We also demonstrate control over motion style, using classifier-free guidance to adjust the strength of the stylistic expression. Experiments on gesture and dance generation confirm that the proposed method achieves top-of-the-line motion quality, with distinctive styles whose expression can be made more or less pronounced. We also synthesise path-driven locomotion using the same model architecture. Finally, we generalise the guidance procedure to obtain product-of-expert ensembles of diffusion models and demonstrate how these may be used for, e.g., style interpolation, a contribution we believe is of independent interest. See https://www.speech.kth.se/research/listen-denoise-action/ for video examples, data, and code.

Few multi-agent reinforcement learning (MARL) research on Google Research Football (GRF) focus on the 11v11 multi-agent full-game scenario and to the best of our knowledge, no open benchmark on this scenario has been released to the public. In this work, we fill the gap by providing a population-based MARL training pipeline and hyperparameter settings on multi-agent football scenario that outperforms the bot with difficulty 1.0 from scratch within 2 million steps. Our experiments serve as a reference for the expected performance of Independent Proximal Policy Optimization (IPPO), a state-of-the-art multi-agent reinforcement learning algorithm where each agent tries to maximize its own policy independently across various training configurations. Meanwhile, we open-source our training framework Light-MALib which extends the MALib codebase by distributed and asynchronized implementation with additional analytical tools for football games. Finally, we provide guidance for building strong football AI with population-based training and release diverse pretrained policies for benchmarking. The goal is to provide the community with a head start for whoever experiment their works on GRF and a simple-to-use population-based training framework for further improving their agents through self-play. The implementation is available at https://github.com/Shanghai-Digital-Brain-Laboratory/DB-Football.

The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the ability to continuously acquire new skills and effectively generalize across a broad range of applications. The advancement of Artificial General Intelligence (AGI) that transcends task and application boundaries is critical for enhancing IDM. Recent studies have extensively investigated the Transformer neural architecture as a foundational model for various tasks, including computer vision, natural language processing, and reinforcement learning. We propose that a Foundation Decision Model (FDM) can be developed by formulating diverse decision-making tasks as sequence decoding tasks using the Transformer architecture, offering a promising solution for expanding IDM applications in complex real-world situations. In this paper, we discuss the efficiency and generalization improvements offered by a foundation decision model for IDM and explore its potential applications in multi-agent game AI, production scheduling, and robotics tasks. Lastly, we present a case study demonstrating our FDM implementation, DigitalBrain (DB1) with 1.3 billion parameters, achieving human-level performance in 870 tasks, such as text generation, image captioning, video game playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 represents an initial step toward more autonomous and efficient real-world IDM applications.

One of the main challenges of multi-agent learning lies in establishing convergence of the algorithms, as, in general, a collection of individual, self-serving agents is not guaranteed to converge with their joint policy, when learning concurrently. This is in stark contrast to most single-agent environments, and sets a prohibitive barrier for deployment in practical applications, as it induces uncertainty in long term behavior of the system. In this work, we apply the concept of trapping regions, known from qualitative theory of dynamical systems, to create safety sets in the joint strategy space for decentralized learning. We propose a binary partitioning algorithm for verification that candidate sets form trapping regions in systems with known learning dynamics, and a heuristic sampling algorithm for scenarios where learning dynamics are not known. We demonstrate the applications to a regularized version of Dirac Generative Adversarial Network, a four-intersection traffic control scenario run in a state of the art open-source microscopic traffic simulator SUMO, and a mathematical model of economic competition.

In multi-agent reinforcement learning (MARL), many popular methods, such as VDN and QMIX, are susceptible to a critical multi-agent pathology known as relative overgeneralization (RO), which arises when the optimal joint action's utility falls below that of a sub-optimal joint action in cooperative tasks. RO can cause the agents to get stuck into local optima or fail to solve cooperative tasks that require significant coordination between agents within a given timestep. Recent value-based MARL algorithms such as QPLEX and WQMIX can overcome RO to some extent. However, our experimental results show that they can still fail to solve cooperative tasks that exhibit strong RO. In this work, we propose a novel approach called curriculum learning for relative overgeneralization (CURO) to better overcome RO. To solve a target task that exhibits strong RO, in CURO, we first fine-tune the reward function of the target task to generate source tasks that are tailored to the current ability of the learning agent and train the agent on these source tasks first. Then, to effectively transfer the knowledge acquired in one task to the next, we use a transfer learning method that combines value function transfer with buffer transfer, which enables more efficient exploration in the target task. We demonstrate that, when applied to QMIX, CURO overcomes severe RO problem and significantly improves performance, yielding state-of-the-art results in a variety of cooperative multi-agent tasks, including the challenging StarCraft II micromanagement benchmarks.

Being able to infer ground truth from the responses of multiple imperfect advisors is a problem of crucial importance in many decision-making applications, such as lending, trading, investment, and crowd-sourcing. In practice, however, gathering answers from a set of advisors has a cost. Therefore, finding an advisor selection strategy that retrieves a reliable answer and maximizes the overall utility is a challenging problem. To address this problem, we propose a novel strategy for optimally selecting a set of advisers in a sequential binary decision-making setting, where multiple decisions need to be made over time. Crucially, we assume no access to ground truth and no prior knowledge about the reliability of advisers. Specifically, our approach considers how to simultaneously (1) select advisors by balancing the advisors' costs and the value of making correct decisions, (2) learn the trustworthiness of advisers dynamically without prior information by asking multiple advisers, and (3) make optimal decisions without access to the ground truth, improving this over time. We evaluate our algorithm through several numerical experiments. The results show that our approach outperforms two other methods that combine state-of-the-art models.

We propose a type of non-cooperative game, termed multi-cluster aggregative game, which is composed of clusters as players, where each cluster consists of collaborative agents with cost functions depending on their own decisions and the aggregate quantity of each participant cluster to modeling large-scale and hierarchical multi-agent systems. This novel game model is motivated by decision-making problems in competitive-cooperative network systems with large-scale nodes, such as the Energy Internet. To address challenges arising in seeking Nash equilibrium for such network systems, we develop an algorithm with a hierarchical communication topology which is a hybrid with distributed and semi-decentralized protocols. The upper level consists of cluster coordinators estimating the aggregate quantities with local communications, while the lower level is cluster subnets composed of its coordinator and agents aiming to track the gradient of the corresponding cluster. In particular, the clusters exchange the aggregate quantities instead of their decisions to relieve the burden of communication. Under strongly monotone and mildly Lipschitz continuous assumptions, we rigorously prove that the algorithm linearly converges to a Nash equilibrium with a fixed step size.We present the applications in the context of the Energy Internet. Furthermore, the numerical results verify the effectiveness of the algorithm.

Several distributed algorithms are presented for the exploration of unknown indoor regions by a swarm of flying, energy constrained agents. The agents, which are identical, autonomous, anonymous and oblivious, uniformly cover the region and thus explore it using predefined action rules based on locally sensed information and the energy level of the agents. While flying drones have many advantages in search and rescue scenarios, their main drawback is a high power consumption during flight combined with limited, on-board energy. Furthermore, in these scenarios agent size is severely limited and consequently so are the total weight and capabilities of the agents. The region is modeled as a connected sub-set of a regular grid composed of square cells that the agents enter, over time, via entry points. Some of the agents may settle in unoccupied cells as the exploration progresses. Settled agents conserve energy and become virtual pheromones for the exploration and coverage process, beacons that subsequently aid the remaining, and still exploring, mobile agents. The termination of the coverage process is based on a backward propagating information diffusion scheme. Various algorithmical alternatives are discussed and upper bounds derived and compared to experimental results. Finally, an optimal entry rate that minimizes the total energy consumption is derived for the case of a linear regions.