In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial attacks has been rarely explored. In this paper, we propose to evaluate the robustness of c-MARL agents via a model-based approach. Our proposed formulation can craft stronger adversarial state perturbations of c-MARL agents(s) to lower total team rewards more than existing model-free approaches. In addition, we propose the first victim-agent selection strategy which allows us to develop even stronger adversarial attack. Numerical experiments on multi-agent MuJoCo benchmarks illustrate the advantage of our approach over other baselines. The proposed model-based attack consistently outperforms other baselines in all tested environments.

Creating reinforcement learning (RL) agents that are capable of accepting and leveraging task-specific knowledge from humans has been long identified as a possible strategy for developing scalable approaches for solving long-horizon problems. While previous works have looked at the possibility of using symbolic models along with RL approaches, they tend to assume that the high-level action models are executable at low level and the fluents can exclusively characterize all desirable MDP states. This need not be true and this assumption overlooks one of the central technical challenges of incorporating symbolic task knowledge, namely, that these symbolic models are going to be an incomplete representation of the underlying task. To this end, we introduce Symbolic-Model Guided Reinforcement Learning, wherein we will formalize the relationship between the symbolic model and the underlying MDP that will allow us to capture the incompleteness of the symbolic model. We will use these models to extract high-level landmarks that will be used to decompose the task, and at the low level, we learn a set of diverse policies for each possible task sub-goal identified by the landmark. We evaluate our system by testing on three different benchmark domains and we show how even with incomplete symbolic model information, our approach is able to discover the task structure and efficiently guide the RL agent towards the goal.

Federated learning makes it possible for all parties with data isolation to train the model collaboratively and efficiently while satisfying privacy protection. To obtain a high-quality model, an incentive mechanism is necessary to motivate more high-quality workers with data and computing power. The existing incentive mechanisms are applied in offline scenarios, where the task publisher collects all bids and selects workers before the task. However, it is practical that different workers arrive online in different orders before or during the task. Therefore, we propose a reverse auction-based online incentive mechanism for horizontal federated learning with budget constraint. Workers submit bids when they arrive online. The task publisher with a limited budget leverages the information of the arrived workers to decide on whether to select the new worker. Theoretical analysis proves that our mechanism satisfies budget feasibility, computational efficiency, individual rationality, consumer sovereignty, time truthfulness, and cost truthfulness with a sufficient budget. The experimental results show that our online mechanism is efficient and can obtain high-quality models.

Control Systems, particularly closed-loop control systems (CLCS), are frequently used in production machines, vehicles, and robots nowadays. CLCS are needed to actively align actual values of a process to a given reference or set values in real-time with a very high precession. Yet, artificial intelligence (AI) is not used to model, design, optimize, and tune CLCS. This paper will highlight potential AI-empowered and -based control system designs and designing procedures, gathering new opportunities and research direction in the field of control system engineering. Therefore, this paper illustrates which building blocks within the standard block diagram of CLCS can be replaced by AI, i.e., artificial neuronal networks (ANN). Having processes with real-time contains and functional safety in mind, it is discussed if AI-based controller blocks can cope with these demands. By concluding the paper, the pros and cons of AI-empowered as well as -based CLCS designs are discussed, and possible research directions for introducing AI in the domain of control system engineering are given.

Machine learning algorithms are often referred to as "black boxes." Once the data is put into the algorithm, it is not always possible to know exactly how the algorithm will reach the prediction. This can be especially frustrating when problems occur. MIT's new Mechanical Engineering (MechE) course teaches students how to combine data science and physics-based engineering to tackle the "black box" problem. In Class 2.C161 (Modeling and Designing Physical Systems Using Machine Learning), Professor George Barbastathis teaches how mechanical engineers use their unique knowledge of physical systems to check algorithms and create more accurate predictions.

In MIT 2.C161, George Barbastathis demonstrates how mechanical engineers can use their knowledge of physical systems to keep algorithms in check and develop more accurate predictions. Machine-learning algorithms are often referred to as a "black box." Once data are put into an algorithm, it's not always known exactly how the algorithm arrives at its prediction. This can be particularly frustrating when things go wrong. A new mechanical engineering (MechE) course at MIT teaches students how to tackle the "black box" problem, through a combination of data science and physics-based engineering.

Scientific machine learning allows us to tackle data-driven modeling in … novel deep learning and traditional physics-based modeling to address …

Federated learning trains models across devices with distributed data, while protecting the privacy and obtaining a model similar to that of centralized ML. A large number of workers with data and computing power are the foundation of federal learning. However, the inevitable costs prevent self-interested workers from serving for free. Moreover, due to data isolation, task publishers lack effective methods to select, evaluate and pay reliable workers with high-quality data. Therefore, we design an auction-based incentive mechanism for horizontal federated learning with reputation and contribution measurement. By designing a reasonable method of measuring contribution, we establish the reputation of workers, which is easy to decline and difficult to improve. Through reverse auctions, workers bid for tasks, and the task publisher selects workers combining reputation and bid price. With the budget constraint, winning workers are paid based on performance. We proved that our mechanism satisfies the individual rationality of the honest worker, budget feasibility, truthfulness, and computational efficiency.

Generalized structural equations models (GSEMs) [Peters and Halpern 2021], are, as the name suggests, a generalization of structural equations models (SEMs). They can deal with (among other things) infinitely many variables with infinite ranges, which is critical for capturing dynamical systems. We provide a sound and complete axiomatization of causal reasoning in GSEMs that is an extension of the sound and complete axiomatization provided by Halpern [2000] for SEMs. Considering GSEMs helps clarify what properties Halpern's axioms capture.

Machine learning methods have recently shown promise in solving partial differential equations (PDEs). They can be classified into two broad categories: approximating the solution function and learning the solution operator. The Physics-Informed Neural Network (PINN) is an example of the former while the Fourier neural operator (FNO) is an example of the latter. Both these approaches have shortcomings. The optimization in PINN is challenging and prone to failure, especially on multi-scale dynamic systems.