Quantum Approximate Optimization Algorithm (QAOA) is one of the leading candidates for demonstrating the quantum advantage using near-term quantum computers. Unfortunately, high device error rates limit us from reliably running QAOA circuits for problems with more than a few qubits. In QAOA, the problem graph is translated into a quantum circuit such that every edge corresponds to two 2-qubit CNOT operations in each layer of the circuit. As CNOTs are extremely error-prone, the fidelity of QAOA circuits is dictated by the number of edges in the problem graph. We observe that majority of graphs corresponding to real-world applications follow the ``power-law`` distribution, where some hotspot nodes have significantly higher number of connections. We leverage this insight and propose ``FrozenQubits`` that freezes the hotspot nodes or qubits and intelligently partitions the state-space of the given problem into several smaller sub-spaces which are then solved independently. The corresponding QAOA sub-circuits are significantly less vulnerable to gate and decoherence errors due to the reduced number of CNOT operations in each sub-circuit. Unlike prior circuit-cutting approaches, FrozenQubits does not require any exponentially complex post-processing step. Our evaluations with 5,300 QAOA circuits on eight different quantum computers from IBM shows that FrozenQubits can improve the quality of solutions by 8.73x on average (and by up to 57x), albeit utilizing 2x more quantum resources.

We formulate an efficient approximation for multi-agent batch reinforcement learning, the approximated multi-agent fitted Q iteration (AMAFQI). We present a detailed derivation of our approach. We propose an iterative policy search and show that it yields a greedy policy with respect to multiple approximations of the centralized, learned Q-function. In each iteration and policy evaluation, AMAFQI requires a number of computations that scales linearly with the number of agents whereas the analogous number of computations increase exponentially for the fitted Q iteration (FQI), a commonly used approaches in batch reinforcement learning. This property of AMAFQI is fundamental for the design of a tractable multi-agent approach. We evaluate the performance of AMAFQI and compare it to FQI in numerical simulations. The simulations illustrate the significant computation time reduction when using AMAFQI instead of FQI in multi-agent problems and corroborate the similar performance of both approaches.

Modern robots require accurate forecasts to make optimal decisions in the real world. For example, self-driving cars need an accurate forecast of other agents' future actions to plan safe trajectories. Current methods rely heavily on historical time series to accurately predict the future. However, relying entirely on the observed history is problematic since it could be corrupted by noise, have outliers, or not completely represent all possible outcomes. To solve this problem, we propose a novel framework for generating robust forecasts for robotic control. In order to model real-world factors affecting future forecasts, we introduce the notion of an adversary, which perturbs observed historical time series to increase a robot's ultimate control cost. Specifically, we model this interaction as a zero-sum two-player game between a robot's forecaster and this hypothetical adversary. We show that our proposed game may be solved to a local Nash equilibrium using gradient-based optimization techniques. Furthermore, we show that a forecaster trained with our method performs 30.14% better on out-of-distribution real-world lane change data than baselines.

Recent advances in learning-based control leverage deep function approximators, such as neural networks, to model the evolution of controlled dynamical systems over time. However, the problem of learning a dynamics model and a stabilizing controller persists, since the synthesis of a stabilizing feedback law for known nonlinear systems is a difficult task, let alone for complex parametric representations that must be fit to data. To this end, we propose Control with Inherent Lyapunov Stability (CoILS), a method for jointly learning parametric representations of a nonlinear dynamics model and a stabilizing controller from data. To do this, our approach simultaneously learns a parametric Lyapunov function which intrinsically constrains the dynamics model to be stabilizable by the learned controller. In addition to the stabilizability of the learned dynamics guaranteed by our novel construction, we show that the learned controller stabilizes the true dynamics under certain assumptions on the fidelity of the learned dynamics. Finally, we demonstrate the efficacy of CoILS on a variety of simulated nonlinear dynamical systems.

Deep learning (DL) has big-data processing capabilities that are as good, or even better, than those of humans in many real-world domains, but at the cost of high energy requirements that may be unsustainable in some applications and of errors, that, though infrequent, can be large. We hypothesise that a fundamental weakness of DL lies in its intrinsic dependence on integrate-and-fire point neurons that maximise information transmission irrespective of whether it is relevant in the current context or not. This leads to unnecessary neural firing and to the feedforward transmission of conflicting messages, which makes learning difficult and processing energy inefficient. Here we show how to circumvent these limitations by mimicking the capabilities of context-sensitive neocortical neurons that receive input from diverse sources as a context to amplify and attenuate the transmission of relevant and irrelevant information, respectively. We demonstrate that a deep network composed of such local processors seeks to maximise agreement between the active neurons, thus restricting the transmission of conflicting information to higher levels and reducing the neural activity required to process large amounts of heterogeneous real-world data. As shown to be far more effective and efficient than current forms of DL, this two-point neuron study offers a possible step-change in transforming the cellular foundations of deep network architectures.

While Huge amounts of unstructured, textual data are most of these studies did not feed the refinement operations generated daily. As more data becomes available, into an iterative retraining process, Smith it becomes more difficult to search, understand et al. (2018) implemented a fully interactive, usercentered and discover the knowledge within it. Because of HL-TM system, and examined how the the human effort it requires, conventional qualitative user experience is affected by issues arising in interactive approaches, such as Grounded Theory, (Glaser systems, such as unpredictability, trust and et al., 1968) are no longer feasible with such large lack of control. However, there are still limitations volumes of data. Topic modelling is a potential to their work. First, their system only allows users solution that has received increasing attention in to refine the model sequentially, meaning that once recent research (Heidenreich et al., 2019; Curiskis a user updates the model, a new model overrides et al., 2020; Dantu et al., 2021; Goyal and Howlett, the previous model. This prevents users from comparing 2021) to help users organize, search, and understand the effects of applying different refinement large amounts of information. It is an unsupervised operations to the same model, making it difficult machine learning technique for identifying to find the most appropriate ones.

Task allocation plays a vital role in multi-robot autonomous cleaning systems, where multiple robots work together to clean a large area. However, most current studies mainly focus on deterministic, single-task allocation for cleaning robots, without considering hybrid tasks in uncertain working environments. Moreover, there is a lack of datasets and benchmarks for relevant research. In this paper, to address these problems, we formulate multi-robot hybrid-task allocation under the uncertain cleaning environment as a robust optimization problem. Firstly, we propose a novel robust mixed-integer linear programming model with practical constraints including the task order constraint for different tasks and the ability constraints of hybrid robots. Secondly, we establish a dataset of \emph{100} instances made from floor plans, each of which has 2D manually-labeled images and a 3D model. Thirdly, we provide comprehensive results on the collected dataset using three traditional optimization approaches and a deep reinforcement learning-based solver. The evaluation results show that our solution meets the needs of multi-robot cleaning task allocation and the robust solver can protect the system from worst-case scenarios with little additional cost. The benchmark will be available at {https://github.com/iamwangyabin/Multi-robot-Cleaning-Task-Allocation}.

This article presents an architecture for multi-agent task allocation and task execution, through the unification of a market-inspired task-auctioning system with Behavior Trees for managing and executing lower level behaviors. We consider the scenario with multi-stage tasks, such as 'pick and place', whose arrival times are not known a priori. In such a scenario, a coordinating architecture is expected to be reactive to newly arrived tasks and the resulting rerouting of agents should be dependent on the stage of completion of their current multi-stage tasks. In the novel architecture proposed in this article, a central auctioning system gathers bids (cost-estimates for completing currently available tasks) from all agents, and solves a combinatorial problem to optimally assign tasks to agents. For every agent, it's participation in the auctioning system and execution of an assigned multi-stage task is managed using behavior trees, which switch among several well-defined behaviors in response to changing scenarios. The auctioning system is run at a fixed rate, allowing for newly added tasks to be incorporated into the auctioning system, which makes the solution reactive and allows for the rerouting of some agents (subject to the states of the behavior trees). We demonstrate that the proposed architecture is especially well-suited for multi-stage tasks, where high costs are incurred when rerouting agents who have completed one or more stages of their current tasks. The scalability analysis of the proposed architecture reveals that it scales well with the number of agents and number of tasks. The proposed framework is experimentally validated in multiple scenarios in a lab environment. A video of a demonstration can be viewed at: https://youtu.be/ZdEkoOOlB2g}.

Bloomberg's announcement that it created a ChatGPT-like large language model focused on finance created a bit of a stir. "BloombergGPT AI may be the harbinger of the next wave of corporate AI," Ethan Mollick, a professor at Wharton, tweeted. He noted that building models is all about the training data and Bloomberg enjoyed the advantage of including proprietary data about finance as well as general information scraped from the Web. Reading the Bloomberg research paper provides some insight into the strange terrain where we find ourselves. Among other things, Bloomberg used a data set called "Enron Emails."

Most deep learning models for computational imaging regress a single reconstructed image. In practice, however, ill-posedness, nonlinearity, model mismatch, and noise often conspire to make such point estimates misleading or insufficient. The Bayesian approach models images and (noisy) measurements as jointly distributed random vectors and aims to approximate the posterior distribution of unknowns. Recent variational inference methods based on conditional normalizing flows are a promising alternative to traditional MCMC methods, but they come with drawbacks: excessive memory and compute demands for moderate to high resolution images and underwhelming performance on hard nonlinear problems. In this work, we propose C-Trumpets -- conditional injective flows specifically designed for imaging problems, which greatly diminish these challenges. Injectivity reduces memory footprint and training time while low-dimensional latent space together with architectural innovations like fixed-volume-change layers and skip-connection revnet layers, C-Trumpets outperform regular conditional flow models on a variety of imaging and image restoration tasks, including limited-view CT and nonlinear inverse scattering, with a lower compute and memory budget. C-Trumpets enable fast approximation of point estimates like MMSE or MAP as well as physically-meaningful uncertainty quantification.