The complete learning of an $n$-qubit quantum state requires samples exponentially in $n$. Several works consider subclasses of quantum states that can be learned in polynomial sample complexity such as stabilizer states or high-temperature Gibbs states. Other works consider a weaker sense of learning, such as PAC learning and shadow tomography. In this work, we consider learning states that are close to neural network quantum states, which can efficiently be represented by a graphical model called restricted Boltzmann machines (RBMs). To this end, we exhibit robustness results for efficient provable two-hop neighborhood learning algorithms for ferromagnetic and locally consistent RBMs. We consider the $L_p$-norm as a measure of closeness, including both total variation distance and max-norm distance in the limit. Our results allow certain quantum states to be learned with a sample complexity \textit{exponentially} better than naive tomography. We hence provide new classes of efficiently learnable quantum states and apply new strategies to learn them.

Current methods of deploying robots that operate in dynamic, uncertain environments, such as Uncrewed Aerial Systems in search \& rescue missions, require nearly continuous human supervision for vehicle guidance and operation. These methods do not consider high-level mission context resulting in cumbersome manual operation or inefficient exhaustive search patterns. We present a human-centered autonomous framework that infers geospatial mission context through dynamic feature sets, which then guides a probabilistic target search planner. Operators provide a set of diverse inputs, including priority definition, spatial semantic information about ad-hoc geographical areas, and reference waypoints, which are probabilistically fused with geographical database information and condensed into a geospatial distribution representing an operator's preferences over an area. An online, POMDP-based planner, optimized for target searching, is augmented with this reward map to generate an operator-constrained policy. Our results, simulated based on input from five professional rescuers, display effective task mental model alignment, 18\% more victim finds, and 15 times more efficient guidance plans then current operational methods.

We study automated intrusion response for an IT infrastructure and formulate the interaction between an attacker and a defender as a partially observed stochastic game. To solve the game we follow an approach where attack and defense strategies co-evolve through reinforcement learning and self-play toward an equilibrium. Solutions proposed in previous work prove the feasibility of this approach for small infrastructures but do not scale to realistic scenarios due to the exponential growth in computational complexity with the infrastructure size. We address this problem by introducing a method that recursively decomposes the game into subgames which can be solved in parallel. Applying optimal stopping theory we show that the best response strategies in these subgames exhibit threshold structures, which allows us to compute them efficiently. To solve the decomposed game we introduce an algorithm called Decompositional Fictitious Self-Play (DFSP), which learns Nash equilibria through stochastic approximation. We evaluate the learned strategies in an emulation environment where real intrusions and response actions can be executed. The results show that the learned strategies approximate an equilibrium and that DFSP significantly outperforms a state-of-the-art algorithm for a realistic infrastructure configuration.

The growing focus on indoor robot navigation utilizing wireless signals has stemmed from the capability of these signals to capture high-resolution angular and temporal measurements. Prior heuristic-based methods, based on radio frequency propagation, are intuitive and generalizable across simple scenarios, yet fail to navigate in complex environments. On the other hand, end-to-end (e2e) deep reinforcement learning (RL), powered by advanced computing machinery, can explore the entire state space, delivering surprising performance when facing complex wireless environments. However, the price to pay is the astronomical amount of training samples, and the resulting policy, without fine-tuning (zero-shot), is unable to navigate efficiently in new scenarios unseen in the training phase. To equip the navigation agent with sample-efficient learning and {zero-shot} generalization, this work proposes a novel physics-informed RL (PIRL) where a distance-to-target-based cost (standard in e2e) is augmented with physics-informed reward shaping. The key intuition is that wireless environments vary, but physics laws persist. After learning to utilize the physics information, the agent can transfer this knowledge across different tasks and navigate in an unknown environment without fine-tuning. The proposed PIRL is evaluated using a wireless digital twin (WDT) built upon simulations of a large class of indoor environments from the AI Habitat dataset augmented with electromagnetic (EM) radiation simulation for wireless signals. It is shown that the PIRL significantly outperforms both e2e RL and heuristic-based solutions in terms of generalization and performance. Source code is available at \url{https://github.com/Panshark/PIRL-WIN}.

Given an observational study with $n$ independent but heterogeneous units, our goal is to learn the counterfactual distribution for each unit using only one $p$-dimensional sample per unit containing covariates, interventions, and outcomes. Specifically, we allow for unobserved confounding that introduces statistical biases between interventions and outcomes as well as exacerbates the heterogeneity across units. Modeling the conditional distribution of the outcomes as an exponential family, we reduce learning the unit-level counterfactual distributions to learning $n$ exponential family distributions with heterogeneous parameters and only one sample per distribution. We introduce a convex objective that pools all $n$ samples to jointly learn all $n$ parameter vectors, and provide a unit-wise mean squared error bound that scales linearly with the metric entropy of the parameter space. For example, when the parameters are $s$-sparse linear combination of $k$ known vectors, the error is $O(s\log k/p)$. En route, we derive sufficient conditions for compactly supported distributions to satisfy the logarithmic Sobolev inequality. As an application of the framework, our results enable consistent imputation of sparsely missing covariates.

Object search is a challenging task because when given complex language descriptions (e.g., "find the white cup on the table"), the robot must move its camera through the environment and recognize the described object. Previous works map language descriptions to a set of fixed object detectors with predetermined noise models, but these approaches are challenging to scale because new detectors need to be made for each object. In this work, we bridge the gap in realistic object search by posing the search problem as a partially observable Markov decision process (POMDP) where the object detector and visual sensor noise in the observation model is determined by a single Deep Neural Network conditioned on complex language descriptions. We incorporate the neural network's outputs into our language-conditioned observation model (LCOM) to represent dynamically changing sensor noise. With an LCOM, any language description of an object can be used to generate an appropriate object detector and noise model, and training an LCOM only requires readily available supervised image-caption datasets. We empirically evaluate our method by comparing against a state-of-the-art object search algorithm in simulation, and demonstrate that planning with our observation model yields a significantly higher average task completion rate (from 0.46 to 0.66) and more efficient and quicker object search than with a fixed-noise model. We demonstrate our method on a Boston Dynamics Spot robot, enabling it to handle complex natural language object descriptions and efficiently find objects in a room-scale environment.

Robust Markov Decision Processes (MDPs) are receiving much attention in learning a robust policy which is less sensitive to environment changes. There are an increasing number of works analyzing sample-efficiency of robust MDPs. However, there are two major barriers to applying robust MDPs in practice. First, most works study robust MDPs in a model-based regime, where the transition probability needs to be estimated and requires a large amount of memories $\mathcal{O}(|\mathcal{S}|^2|\mathcal{A}|)$. Second, prior work typically assumes a strong oracle to obtain the optimal solution as an intermediate step to solve robust MDPs. However, in practice, such an oracle does not exist usually. To remove the oracle, we transform the original robust MDPs into an alternative form, which allows us to use stochastic gradient methods to solve the robust MDPs. Moreover, we prove the alternative form still plays a similar role as the original form. With this new formulation, we devise a sample-efficient algorithm to solve the robust MDPs in a model-free regime, which does not require an oracle and trades off a lower storage requirement $\mathcal{O}(|\mathcal{S}||\mathcal{A}|)$ with being able to generate samples from a generative model or Markovian chain. Finally, we validate our theoretical findings via numerical experiments, showing the efficiency with the alternative form of robust MDPs.

This paper presents a novel hybrid Automatic Speech Recognition (ASR) system designed specifically for resource-constrained robots. The proposed approach combines Hidden Markov Models (HMMs) with deep learning models and leverages socket programming to distribute processing tasks effectively. In this architecture, the HMM-based processing takes place within the robot, while a separate PC handles the deep learning model. This synergy between HMMs and deep learning enhances speech recognition accuracy significantly. We conducted experiments across various robotic platforms, demonstrating real-time and precise speech recognition capabilities. Notably, the system exhibits adaptability to changing acoustic conditions and compatibility with low-power hardware, making it highly effective in environments with limited computational resources. This hybrid ASR paradigm opens up promising possibilities for seamless human-robot interaction. In conclusion, our research introduces a pioneering dimension to ASR techniques tailored for robotics. By employing socket programming to distribute processing tasks across distinct devices and strategically combining HMMs with deep learning models, our hybrid ASR system showcases its potential to enable robots to comprehend and respond to spoken language adeptly, even in environments with restricted computational resources. This paradigm sets a innovative course for enhancing human-robot interaction across a wide range of real-world scenarios.

This study explores the potential of reinforcement learning algorithms to enhance career planning processes. Leveraging data from Randstad The Netherlands, the study simulates the Dutch job market and develops strategies to optimize employees' long-term income. By formulating career planning as a Markov Decision Process (MDP) and utilizing machine learning algorithms such as Sarsa, Q-Learning, and A2C, we learn optimal policies that recommend career paths with high-income occupations and industries. The results demonstrate significant improvements in employees' income trajectories, with RL models, particularly Q-Learning and Sarsa, achieving an average increase of 5% compared to observed career paths. The study acknowledges limitations, including narrow job filtering, simplifications in the environment formulation, and assumptions regarding employment continuity and zero application costs. Future research can explore additional objectives beyond income optimization and address these limitations to further enhance career planning processes.

In this paper, we present a transformer architecture for predicting student performance on standardized tests. Specifically, we leverage students historical data, including their past test scores, study habits, and other relevant information, to create a personalized model for each student. We then use these models to predict their future performance on a given test. Applying this model to the RIIID dataset, we demonstrate that using multiple granularities for temporal features as the decoder input significantly improve model performance. Our results also show the effectiveness of our approach, with substantial improvements over the LightGBM method. Our work contributes to the growing field of AI in education, providing a scalable and accurate tool for predicting student outcomes.