Centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to epsilon-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. This paper presents a novel and more scalable alternative, namely sequential-move centralized training for decentralized execution. This paradigm further pushes the applicability of Bellman's principle of optimality, raising three new properties. First, it allows a central planner to reason upon sufficient sequential-move statistics instead of prior simultaneous-move ones. Next, it proves that epsilon-optimal value functions are piecewise linear and convex in sufficient sequential-move statistics. Finally, it drops the complexity of the backup operators from double exponential to polynomial at the expense of longer planning horizons. Besides, it makes it easy to use single-agent methods, e.g., SARSA algorithm enhanced with these findings applies while still preserving convergence guarantees. Experiments on two- as well as many-agent domains from the literature against epsilon-optimal simultaneous-move solvers confirm the superiority of the novel approach. This paradigm opens the door for efficient planning and reinforcement learning methods for multi-agent systems.

With more autonomous vehicles (AVs) sharing roadways with human-driven vehicles (HVs), ensuring safe and courteous maneuvers that respect HVs' behavior becomes increasingly important. To promote both safety and courtesy in AV's behavior, an extension of Control Barrier Functions (CBFs)-inspired risk evaluation framework is proposed in this paper by considering both noisy observed positions and velocities of surrounding vehicles. The perceived risk by the ego vehicle can be visualized as a risk map that reflects the understanding of the surrounding environment and thus shows the potential for facilitating safe and courteous driving. By incorporating the risk evaluation framework into the Model Predictive Control (MPC) scheme, we propose a Courteous MPC for ego AV to generate courteous behaviors that 1) reduce the overall risk imposed on other vehicles and 2) respect the hard safety constraints and the original objective for efficiency. We demonstrate the performance of the proposed Courteous MPC via theoretical analysis and simulation experiments.

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of violating a given safety specification. Such a risk evaluation would need to be performed at run-time to provide a guardrail against dangerous actions of an AI. Noting that different plausible hypotheses about the world could produce very different outcomes, and because we do not know which one is right, we derive bounds on the safety violation probability predicted under the true but unknown hypothesis. Such bounds could be used to reject potentially dangerous actions. Our main results involve searching for cautious but plausible hypotheses, obtained by a maximization that involves Bayesian posteriors over hypotheses. We consider two forms of this result, in the iid case and in the non-iid case, and conclude with open problems towards turning such theoretical results into practical AI guardrails.

Control affine assumptions, human inputs are external disturbances, in certified safe controller synthesis approaches are frequently violated in operational deployment under causal human actions. This paper takes a human-in-the-loop human-in-the-plant (HIL-HIP) approach towards ensuring operational safety of safety critical autonomous systems: human and real world controller (RWC) are modeled as a unified system. A three-way interaction is considered: a) through personalized inputs and biological feedback processes between HIP and HIL, b) through sensors and actuators between RWC and HIP, and c) through personalized configuration changes and data feedback between HIL and RWC. We extend control Lyapunov theory by generating barrier function (CLBF) under human action plans, model the HIL as a combination of Markov Chain for spontaneous events and Fuzzy inference system for event responses, the RWC as a black box, and integrate the HIL-HIP model with neural architectures that can learn CLBF certificates. We show that synthesized HIL-HIP controller for automated insulin delivery in Type 1 Diabetes is the only controller to meet safety requirements for human action inputs.

The superiority of Multi-Robot Systems (MRS) in various complex environments is unquestionable. However, in complex situations such as search and rescue, environmental monitoring, and automated production, robots are often required to work collaboratively without a central control unit. This necessitates an efficient and robust decentralized control mechanism to process local information and guide the robots' behavior. In this work, we propose a new decentralized controller design method that utilizes the Deep Q-Network (DQN) algorithm from deep reinforcement learning, aimed at improving the integration of local information and robustness of multi-robot systems. The designed controller allows each robot to make decisions independently based on its local observations while enhancing the overall system's collaborative efficiency and adaptability to dynamic environments through a shared learning mechanism. Through testing in simulated environments, we have demonstrated the effectiveness of this controller in improving task execution efficiency, strengthening system fault tolerance, and enhancing adaptability to the environment. Furthermore, we explored the impact of DQN parameter tuning on system performance, providing insights for further optimization of the controller design. Our research not only showcases the potential application of the DQN algorithm in the decentralized control of multi-robot systems but also offers a new perspective on how to enhance the overall performance and robustness of the system through the integration of local information.

This study addresses the challenge of fleet design optimization in the context of heterogeneous multi-robot fleets, aiming to obtain feasible designs that balance performance and costs. In the domain of autonomous multi-robot exploration, reinforcement learning agents play a central role, offering adaptability to complex terrains and facilitating collaboration among robots. However, modifying the fleet composition results in changes in the learned behavior, and training multi-robot systems using multi-agent reinforcement learning is expensive. Therefore, an exhaustive evaluation of each potential fleet design is infeasible. To tackle these hurdles, we introduce Bayesian Optimization for Fleet Design (BOFD), a framework leveraging multi-objective Bayesian Optimization to explore fleets on the Pareto front of performance and cost while accounting for uncertainty in the design space. Moreover, we establish a sub-linear bound for cumulative regret, supporting BOFD's robustness and efficacy. Extensive benchmark experiments in synthetic and simulated environments demonstrate the superiority of our framework over state-of-the-art methods, achieving efficient fleet designs with minimal fleet evaluations.

We present a probabilistic model for stochastic iterative algorithms with the use case of optimization algorithms in mind. Based on this model, we present PAC-Bayesian generalization bounds for functions that are defined on the trajectory of the learned algorithm, for example, the expected (non-asymptotic) convergence rate and the expected time to reach the stopping criterion. Thus, not only does this model allow for learning stochastic algorithms based on their empirical performance, it also yields results about their actual convergence rate and their actual convergence time. We stress that, since the model is valid in a more general setting than learning-to-optimize, it is of interest for other fields of application, too. Finally, we conduct five practically relevant experiments, showing the validity of our claims.

Constrained Markov Decision Process (CMDP) is a classical framework where an agent repeatedly interacts with an unknown environment to maximize the cumulative discounted rewards while simultaneously ensuring that the cumulative observed costs are within a pre-defined boundary. It finds its application in a multitude of practical scenarios. For example, consider an autonomous vehicle that attempts to reach its destination via the shortest-time route without violating traffic rules or a corporate leader who aims to maximize revenue without crossing a monetary budget. In these cases, any departure from the boundary set by the predefined rules can be signaled by a cost while the progress towards the desired objective can be indicated by a reward. Finding an optimal policy to navigate an unknown CMDP is a difficult task. Nevertheless, several recent articles have proposed algorithms to solve this challenging problem with optimality guarantees.

We propose a procedure for estimating the Schr\"odinger bridge between two probability distributions. Unlike existing approaches, our method does not require iteratively simulating forward and backward diffusions or training neural networks to fit unknown drifts. Instead, we show that the potentials obtained from solving the static entropic optimal transport problem between the source and target samples can be modified to yield a natural plug-in estimator of the time-dependent drift that defines the bridge between two measures. Under minimal assumptions, we show that our proposal, which we call the \emph{Sinkhorn bridge}, provably estimates the Schr\"odinger bridge with a rate of convergence that depends on the intrinsic dimensionality of the target measure. Our approach combines results from the areas of sampling, and theoretical and statistical entropic optimal transport.

Advanced probabilistic programming languages (PPLs) use hybrid inference systems to combine symbolic exact inference and Monte Carlo methods to improve inference performance. These systems use heuristics to partition random variables within the program into variables that are encoded symbolically and variables that are encoded with sampled values, and the heuristics are not necessarily aligned with the performance evaluation metrics used by the developer. In this work, we present inference plans, a programming interface that enables developers to control the partitioning of random variables during hybrid particle filtering. We further present Siren, a new PPL that enables developers to use annotations to specify inference plans the inference system must implement. To assist developers with statically reasoning about whether an inference plan can be implemented, we present an abstract-interpretation-based static analysis for Siren for determining inference plan satisfiability. We prove the analysis is sound with respect to Siren's semantics. Our evaluation applies inference plans to three different hybrid particle filtering algorithms on a suite of benchmarks and shows that the control provided by inference plans enables speed ups of 1.76x on average and up to 206x to reach target accuracy, compared to the inference plans implemented by default heuristics; the results also show that inference plans improve accuracy by 1.83x on average and up to 595x with less or equal runtime, compared to the default inference plans. We further show that the static analysis is precise in practice, identifying all satisfiable inference plans in 27 out of the 33 benchmark-algorithm combinations.