Although the field of multi-agent reinforcement learning (MARL) has made considerable progress in the last years, solving systems with a large number of agents remains a hard challenge. Graphon mean field games (GMFGs) enable the scalable analysis of MARL problems that are otherwise intractable. By the mathematical structure of graphons, this approach is limited to dense graphs which are insufficient to describe many real-world networks such as power law graphs. Our paper introduces a novel formulation of GMFGs, called LPGMFGs, which leverages the graph theoretical concept of $L^p$ graphons and provides a machine learning tool to efficiently and accurately approximate solutions for sparse network problems. This especially includes power law networks which are empirically observed in various application areas and cannot be captured by standard graphons. We derive theoretical existence and convergence guarantees and give empirical examples that demonstrate the accuracy of our learning approach for systems with many agents. Furthermore, we extend the Online Mirror Descent (OMD) learning algorithm to our setup to accelerate learning speed, empirically show its capabilities, and conduct a theoretical analysis using the novel concept of smoothed step graphons. In general, we provide a scalable, mathematically well-founded machine learning approach to a large class of otherwise intractable problems of great relevance in numerous research fields.

Existing multi-agent perception systems assume that every agent utilizes the same model with identical parameters and architecture. The performance can be degraded with different perception models due to the mismatch in their confidence scores. In this work, we propose a model-agnostic multi-agent perception framework to reduce the negative effect caused by the model discrepancies without sharing the model information. Specifically, we propose a confidence calibrator that can eliminate the prediction confidence score bias. Each agent performs such calibration independently on a standard public database to protect intellectual property. We also propose a corresponding bounding box aggregation algorithm that considers the confidence scores and the spatial agreement of neighboring boxes. Our experiments shed light on the necessity of model calibration across different agents, and the results show that the proposed framework improves the baseline 3D object detection performance of heterogeneous agents.

Communication technologies enable coordination among connected and autonomous vehicles (CAVs). However, it remains unclear how to utilize shared information to improve the safety and efficiency of the CAV system in dynamic and complicated driving scenarios. In this work, we propose a framework of constrained multi-agent reinforcement learning (MARL) with a parallel Safety Shield for CAVs in challenging driving scenarios that includes unconnected hazard vehicles. The coordination mechanisms of the proposed MARL include information sharing and cooperative policy learning, with Graph Convolutional Network (GCN)-Transformer as a spatial-temporal encoder that enhances the agent's environment awareness. The Safety Shield module with Control Barrier Functions (CBF)-based safety checking protects the agents from taking unsafe actions. We design a constrained multi-agent advantage actor-critic (CMAA2C) algorithm to train safe and cooperative policies for CAVs. With the experiment deployed in the CARLA simulator, we verify the performance of the safety checking, spatial-temporal encoder, and coordination mechanisms designed in our method by comparative experiments in several challenging scenarios with unconnected hazard vehicles. Results show that our proposed methodology significantly increases system safety and efficiency in challenging scenarios.

The physical autonomy of robots is well understood both theoretically and practically. By contrast, there is almost no research exploring their potential economic autonomy. In this paper, we present the first economically autonomous robot -- a robot able to produce marketable goods while having full control over the use of its generated income. Gaka-chu ("painter" in Japanese) is a 6-axis robot arm that creates paintings of Japanese characters from an autoselected keyword. By using a blockchain-based smart contract, Gaka-chu can autonomously list a painting it made for sale in an online auction. In this transaction, the robot interacts with the human bidders as a peer not as a tool. Using the blockchain-based smart contract, Gaka-chu can then use its income from selling paintings to replenish its resources by autonomously ordering materials from an online art shop. We built the Gaka-chu prototype with an Ethereum-based smart contract and ran a 6-month long experiment, during which the robot created and sold four paintings, simultaneously using its income to purchase supplies and repay initial investors. In this work, we present the results of the experiments conducted and discuss the implications of economically autonomous robots.

Collaboration is an essential function of multiplayer game such as a MOBA, and Soccer game. In the case of Reinforcement Learning, the transition probabilities should be stationary in order to be trained well. Due to this point, famous early study of the OpenAI tried to apply a additional method to deal with the fluctuating transition probabilities. However, recent research of the DeepMind for MARL say that multiple agent game also can be converged to the Nash Equilibrium despite of unstable transition probability. In theory such multi-agent systems may continue to explore forever.

Ad-hoc team cooperation is the problem of cooperating with other players that have not been seen in the learning process. Recently, this problem has been considered in the context of Hanabi, which requires cooperation without explicit communication with the other players. While in self-play strategies cooperating on reinforcement learning (RL) process has shown success, there is the problem of failing to cooperate with other unseen agents after the initial learning is completed. In this paper, we categorize the results of ad-hoc team cooperation into Failure, Success, and Synergy and analyze the associated failures. First, we confirm that agents learning via RL converge to one strategy each, but not necessarily the same strategy and that these agents can deploy different strategies even though they utilize the same hyperparameters. Second, we confirm that the larger the behavioral difference, the more pronounced the failure of ad-hoc team cooperation, as demonstrated using hierarchical clustering and Pearson correlation. We confirm that such agents are grouped into distinctly different groups through hierarchical clustering, such that the correlation between behavioral differences and ad-hoc team performance is -0.978. Our results improve understanding of key factors to form successful ad-hoc team cooperation in multi-player games.

In conceptual modeling (CM), humans apply abstraction to represent excerpts of reality for means of understanding and communication, and processing by machines. Artificial Intelligence (AI) is applied to vast amounts of data to automatically identify patterns or classify entities. While CM produces comprehensible and explicit knowledge representations, the outcome of AI algorithms often lacks these qualities while being able to extract knowledge from large and unstructured representations. Recently, a trend toward intertwining CM and AI emerged. This systematic mapping study shows how this interdisciplinary research field is structured, which mutual benefits are gained by the intertwining, and future research directions.

-- We consider the open federated learning (FL) systems, where clients may join and/or leave the system during the FL process. Given the variability of the number of present clients, convergence to a fixed model cannot be guaranteed in open systems. Instead, we resort to a new performance metric that we term the stability of open FL systems, which quantifies the magnitude of the learned model in open systems. Under the assumption that local clients' functions are strongly convex and smooth, we theoretically quantify the radius of stability for two FL algorithms, namely local SGD and local Adam. We observe that this radius relies on several key parameters, including the function condition number as well as the variance of the stochastic gradient. Our theoretical results are further verified by numerical simulations on synthetic data. Federated learning (FL) [1] is a machine learning setup where a group of clients work cooperatively to learn a statistical model. The learning process is coordinated by a central server which facilitates the exchange of model updates. FL algorithms enjoy the benefits of model sharing among clients while preserving data privacy, and they also reduce the number of communications without making too much sacrifice on the performance [2]. In a canonical FL algorithm, the central server broadcasts the initial model to all clients, and then, each client performs several steps of local updates before sending the model to the server.

Current approaches to multi-agent cooperation rely heavily on centralized mechanisms or explicit communication protocols to ensure convergence. This paper studies the problem of distributed multi-agent learning without resorting to centralized components or explicit communication. It examines the use of distribution matching to facilitate the coordination of independent agents. In the proposed scheme, each agent independently minimizes the distribution mismatch to the corresponding component of a target visitation distribution. The theoretical analysis shows that under certain conditions, each agent minimizing its individual distribution mismatch allows the convergence to the joint policy that generated the target distribution. Further, if the target distribution is from a joint policy that optimizes a cooperative task, the optimal policy for a combination of this task reward and the distribution matching reward is the same joint policy. This insight is used to formulate a practical algorithm (DM$^2$), in which each individual agent matches a target distribution derived from concurrently sampled trajectories from a joint expert policy. Experimental validation on the StarCraft domain shows that combining (1) a task reward, and (2) a distribution matching reward for expert demonstrations for the same task, allows agents to outperform a naive distributed baseline. Additional experiments probe the conditions under which expert demonstrations need to be sampled to obtain the learning benefits.

This work focuses on the persistent monitoring problem, where a set of targets moving based on an unknown model must be monitored by an autonomous mobile robot with a limited sensing range. To keep each target's position estimate as accurate as possible, the robot needs to adaptively plan its path to (re-)visit all the targets and update its belief from measurements collected along the way. In doing so, the main challenge is to strike a balance between exploitation, i.e., re-visiting previously-located targets, and exploration, i.e., finding new targets or re-acquiring lost ones. Encouraged by recent advances in deep reinforcement learning, we introduce an attention-based neural solution to the persistent monitoring problem, where the agent can learn the inter-dependencies between targets, i.e., their spatial and temporal correlations, conditioned on past measurements. This endows the agent with the ability to determine which target, time, and location to attend to across multiple scales, which we show also helps relax the usual limitations of a finite target set. We experimentally demonstrate that our method outperforms other baselines in terms of number of targets visits and average estimation error in complex environments. Finally, we implement and validate our model in a drone-based simulation experiment to monitor mobile ground targets in a high-fidelity simulator.