Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and reinforcement learning. This article surveys some of the recent developments on policy optimization, a gradient-based iterative approach for feedback control synthesis, popularized by successes of reinforcement learning. We take an interdisciplinary perspective in our exposition that connects control theory, reinforcement learning, and large-scale optimization. We review a number of recently-developed theoretical results on the optimization landscape, global convergence, and sample complexity of gradient-based methods for various continuous control problems such as the linear quadratic regulator (LQR), $\mathcal{H}_\infty$ control, risk-sensitive control, linear quadratic Gaussian (LQG) control, and output feedback synthesis. In conjunction with these optimization results, we also discuss how direct policy optimization handles stability and robustness concerns in learning-based control, two main desiderata in control engineering. We conclude the survey by pointing out several challenges and opportunities at the intersection of learning and control.

The control problem of a multi-copter swarm, mechanically coupled through a modular lattice structure of connecting rods, is considered in this article. The system's structural elasticity is considered in deriving the system's dynamics. The devised controller is robust against the induced flexibilities, while an inherent adaptation scheme allows for the control of asymmetrical configurations and the transportation of unknown payloads. Certain optimization metrics are introduced for solving the individual agent thrust allocation problem while achieving maximum system flight time, resulting in a platform-independent control implementation. Experimental studies are offered to illustrate the efficiency of the suggested controller under typical flight conditions, increased rod elasticities and payload transportation.

Synchronizing decisions across multiple agents in realistic settings is problematic since it requires agents to wait for other agents to terminate and communicate about termination reliably. Ideally, agents should learn and execute asynchronously instead. Such asynchronous methods also allow temporally extended actions that can take different amounts of time based on the situation and action executed. Unfortunately, current policy gradient methods are not applicable in asynchronous settings, as they assume that agents synchronously reason about action selection at every time step. To allow asynchronous learning and decision-making, we formulate a set of asynchronous multi-agent actor-critic methods that allow agents to directly optimize asynchronous policies in three standard training paradigms: decentralized learning, centralized learning, and centralized training for decentralized execution. Empirical results (in simulation and hardware) in a variety of realistic domains demonstrate the superiority of our approaches in large multi-agent problems and validate the effectiveness of our algorithms for learning high-quality and asynchronous solutions.

The state-of-the-art multi-agent reinforcement learning (MARL) methods have provided promising solutions to a variety of complex problems. Yet, these methods all assume that agents perform synchronized primitive-action executions so that they are not genuinely scalable to long-horizon real-world multi-agent/robot tasks that inherently require agents/robots to asynchronously reason about high-level action selection at varying time durations. The Macro-Action Decentralized Partially Observable Markov Decision Process (MacDec-POMDP) is a general formalization for asynchronous decision-making under uncertainty in fully cooperative multi-agent tasks. In this thesis, we first propose a group of value-based RL approaches for MacDec-POMDPs, where agents are allowed to perform asynchronous learning and decision-making with macro-action-value functions in three paradigms: decentralized learning and control, centralized learning and control, and centralized training for decentralized execution (CTDE). Building on the above work, we formulate a set of macro-action-based policy gradient algorithms under the three training paradigms, where agents are allowed to directly optimize their parameterized policies in an asynchronous manner. We evaluate our methods both in simulation and on real robots over a variety of realistic domains. Empirical results demonstrate the superiority of our approaches in large multi-agent problems and validate the effectiveness of our algorithms for learning high-quality and asynchronous solutions with macro-actions.

We generalise the problem of reward modelling (RM) for reinforcement learning (RL) to handle non-Markovian rewards. Existing work assumes that human evaluators observe each step in a trajectory independently when providing feedback on agent behaviour. In this work, we remove this assumption, extending RM to capture temporal dependencies in human assessment of trajectories. We show how RM can be approached as a multiple instance learning (MIL) problem, where trajectories are treated as bags with return labels, and steps within the trajectories are instances with unseen reward labels. We go on to develop new MIL models that are able to capture the time dependencies in labelled trajectories. We demonstrate on a range of RL tasks that our novel MIL models can reconstruct reward functions to a high level of accuracy, and can be used to train high-performing agent policies.

Algorithm configuration (AC) is concerned with the automated search of the most suitable parameter configuration of a parametrized algorithm. There is currently a wide variety of AC problem variants and methods proposed in the literature. Existing reviews do not take into account all derivatives of the AC problem, nor do they offer a complete classification scheme. To this end, we introduce taxonomies to describe the AC problem and features of configuration methods, respectively. We review existing AC literature within the lens of our taxonomies, outline relevant design choices of configuration approaches, contrast methods and problem variants against each other, and describe the state of AC in industry. Finally, our review provides researchers and practitioners with a look at future research directions in the field of AC.

This paper designs methods for decentralized multiple hypothesis testing on graphs that are equipped with provable guarantees on the false discovery rate (FDR). We consider the setting where distinct agents reside on the nodes of an undirected graph, and each agent possesses p-values corresponding to one or more hypotheses local to its node. Each agent must individually decide whether to reject one or more of its local hypotheses by only communicating with its neighbors, with the joint aim that the global FDR over the entire graph must be controlled at a predefined level. We propose a simple decentralized family of Query-Test-Exchange (QuTE) algorithms and prove that they can control FDR under independence or positive dependence of the p-values. Our algorithm reduces to the Benjamini-Hochberg (BH) algorithm when after graph-diameter rounds of communication, and to the Bonferroni procedure when no communication has occurred or the graph is empty. To avoid communicating real-valued p-values, we develop a quantized BH procedure, and extend it to a quantized QuTE procedure. QuTE works seamlessly in streaming data settings, where anytime-valid p-values may be continually updated at each node. Last, QuTE is robust to arbitrary dropping of packets, or a graph that changes at every step, making it particularly suitable to mobile sensor networks involving drones or other multi-agent systems. We study the power of our procedure using a simulation suite of different levels of connectivity and communication on a variety of graph structures, and also provide an illustrative real-world example.

To achieve desirable performance, current AI systems often require huge amounts of training data. This is especially problematic in domains where collecting data is both expensive and time-consuming, e.g., where AI systems require having numerous interactions with humans, collecting feedback from them. In this work, we substantiate the idea of $\textit{cognitive models as simulators}$, which is to have AI systems interact with, and collect feedback from, cognitive models instead of humans, thereby making their training process both less costly and faster. Here, we leverage this idea in the context of moral decision-making, by having reinforcement learning (RL) agents learn about fairness through interacting with a cognitive model of the Ultimatum Game (UG), a canonical task in behavioral and brain sciences for studying fairness. Interestingly, these RL agents learn to rationally adapt their behavior depending on the emotional state of their simulated UG responder. Our work suggests that using cognitive models as simulators of humans is an effective approach for training AI systems, presenting an important way for computational cognitive science to make contributions to AI.

In this study, we synthesize a novel dynamical approach for ant colonies enabling them to migrate to new nest sites in a self-organizing fashion. In other words, we realize ant colony migration as a self-organizing phenotype-level collective behavior. For this purpose, we first segment the edges of the graph of ants' pathways. Then, each segment, attributed to its own pheromone profile, may host an ant. So, multiple ants may occupy an edge at the same time. Thanks to this segment-wise edge formulation, ants have more selection options in the course of their pathway determination, thereby increasing the diversity of their colony's emergent behaviors. In light of the continuous pheromone dynamics of segments, each edge owns a spatio-temporal piece-wise continuous pheromone profile in which both deposit and evaporation processes are unified. The passive dynamics of the proposed migration mechanism is sufficiently rich so that an ant colony can migrate to the vicinity of a new nest site in a self-organizing manner without any external supervision. In particular, we perform extensive simulations to test our migration dynamics applied to a colony including 500 ants traversing a pathway graph comprising 200 nodes and 4000 edges which are segmented based on various resolutions. The obtained results exhibit the effectiveness of our strategy.

Understanding human tasks through video observations is an essential capability of intelligent agents. The challenges of such capability lie in the difficulty of generating a detailed understanding of situated actions, their effects on object states (i.e., state changes), and their causal dependencies. These challenges are further aggravated by the natural parallelism from multi-tasking and partial observations in multi-agent collaboration. Most prior works leverage action localization or future prediction as an indirect metric for evaluating such task understanding from videos. To make a direct evaluation, we introduce the EgoTaskQA benchmark that provides a single home for the crucial dimensions of task understanding through question-answering on real-world egocentric videos. We meticulously design questions that target the understanding of (1) action dependencies and effects, (2) intents and goals, and (3) agents' beliefs about others. These questions are divided into four types, including descriptive (what status?), predictive (what will?), explanatory (what caused?), and counterfactual (what if?) to provide diagnostic analyses on spatial, temporal, and causal understandings of goal-oriented tasks. We evaluate state-of-the-art video reasoning models on our benchmark and show their significant gaps between humans in understanding complex goal-oriented egocentric videos. We hope this effort will drive the vision community to move onward with goal-oriented video understanding and reasoning.